Our Publications

Note: Some of our publications are not available for public access. If you need an electronic version of one of these papers, feel free to contact the author.

 Publications 2017
 Publications 2016
 Publications 2015
 Publications until 2014

2017

Henry Bradler, Matthias Ochs, Nolang Fanani, Rudolf Mester:
Joint Epipolar Tracking (JET): Simultaneous optimization of epipolar geometry and feature correspondences
IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, USA, March 2017
Show abstract

Traditionally, pose estimation is considered as a two step problem. First, feature correspondences are determined by direct comparison of image patches, or by associating feature descriptors. In a second step, the relative pose and the coordinates of corresponding points are estimated, most often by minimizing the reprojection error (RPE). RPE optimization is based on a loss function that is merely aware of the feature pixel positions but not of the underlying image intensities. In this paper, we propose a sparse direct method which introduces a loss function that allows to simultaneously optimize the unscaled relative pose, as well as the set of feature correspondences directly considering the image intensity values. Furthermore, we show how to integrate statistical prior information on the motion into the optimization process. This constructive inclusion of a Bayesian bias term is particularly efficient in application cases with a strongly predictable (short term) dynamic, e.g. in a driving scenario. In our experiments, we demonstrate that the 'JET' algorithm we propose outperforms the classical reprojection error optimization on two synthetic datasets and on the KITTI dataset. The JET algorithm runs in real-time on a single CPU thread.

Hide abstract

2016

Jan van den Brand, Matthias Ochs, Rudolf Mester:
Instance-level Segmentation of Vehicles using Deep Contours
Asian Conference on Computer Vision - Workshop on Computer Vision Technologies for Smart Vehicle, Taipei, Taiwan, November 2016
Show abstract

The recognition of individual object instances in single monoc- ular images is still an incompletely solved task. In this work, we propose a new approach for detecting and separating vehicles in the context of autonomous driving. Our method uses the fully convolutional network (FCN) for semantic labeling and for estimating the boundary of each vehicle. Even though a contour is in general a one pixel wide structure which cannot be directly learned by a CNN, our network addresses this by providing areas around the contours. Based on these areas, we sepa- rate the individual vehicle instances. In our experiments, we show on two challenging datasets (Cityscapes and KITTI) that we achieve state-of- the-art performance, despite the usage of a subsampling rate of two. Our approach even outperforms all recent works w.r.t. several rating scores.

Hide abstract

Peter Pinggera*, Sebastian Ramos, Stefan Gehrig, Uwe Franke, Carsten Rother, Rudolf Mester:
Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles
International Conference on Intelligent Robots and Systems (IROS), Daejeon, Korea, October 2016
Show abstract

Detecting small obstacles on the road ahead is a critical part of the driving task which has to be mastered by fully autonomous cars. In this paper, we present a method based on stereo vision to reliably detect such obstacles from a moving vehicle. The proposed algorithm performs statistical hypothesis tests in disparity space directly on stereo image data, assessing freespace and obstacle hypotheses on independent local patches. This detection approach does not depend on a global road model and handles both static and moving obstacles. For evaluation, we employ a novel lost-cargo image sequence dataset comprising more than two thousand frames with pixelwise annotations of obstacle and free-space and provide a thorough comparison to several stereo-based baseline methods. The dataset will be made available to the community to foster further research on this important topic. The proposed approach outperforms all considered baselines in our evaluations on both pixel and object level and runs at frame rates of up to 20 Hz on 2 mega-pixel stereo imagery. Small obstacles down to the height of 5 cm can successfully be detected at 20 m distance at low false positive rates.

Hide abstract

Christian Conrad, Rudolf Mester:
Learning Rank Reduced Mappings using Canonical Correlation Analysis Statistical Signal Processing Workshop (SSP), Palma de Mallorca, Spain, June 2016
Show abstract

Correspondence relations between different views of the same scene can be learnt in an unsupervised manner. We address autonomous learning of arbitrary fixed spatial (point-to-point) mappings. Since any such transformation can be represented by a permutation matrix, the signal model is a linear one, whereas the proposed analysis method, mainly based on Canonical Correlation Analysis} (CCA) is based on a generalized eigensystem problem, i.e. a nonlinear operation. The learnt transformation is represented implicitly in terms of pairs of learned basis vectors and does neither use nor require an analytic / parametric expression for the latent mapping. We show how the rank of the signal that is shared among views may be determined from canonical correlations and how the overlapping (=shared) dimensions among the views may be inferred.

Hide abstract

Daniel Biedermann, Matthias Ochs, Rudolf Mester:
Evaluating visual ADAS components on the COnGRATS dataset Intelligent Vehicles Symposium (IV), Gothenburg, Sweden, June 2016
Show abstract

To aid in the development and evaluation of vision algorithms in the context of driver assistance applications and traffic surveillance, we created a framework that allows us for continuous creation of highly realistic image sequences featuring traffic scenarios. The sequences are created with a realistic and state of the art vehicle physics model and different kinds of environments are featured, thus providing a wide range of testing scenarios. Due to the physically-based rendering technique and camera model that is employed for the image rendering process, we can simulate different sensor setups and provide appropriate and fully accurate ground truth data for them.

Hide abstract

Nolang Fanani*, Rudolf Mester:
Keypoint Trajectory Estimation Using Propagation Based Tracking Intelligent Vehicles Symposium (IV), Gothenburg, Sweden, June 2016
Show abstract

Driver assistance has been a major applicationfield in recent decades. One of the major steps of structure-from-motion approaches is to track surrounding keypointsand to recognize the trajectories of the keypoints. This paperpresents a method to obtain the trajectories of keypoints from asequence of images. The keypoint trajectories are accumulatedby implementing keypoint tracking through the propagationof the predicted 3D position of the keypoint. Experiments onthe KITTI dataset as well as on a synthetic dataset show thataccurate keypoint trajectories are attainable.

Hide abstract

Nolang Fanani, Matthias Ochs, Henry Bradler, Rudolf Mester:
Propagation based tracking with uncertainty measurement in automotive application Southwest Symposium on Image Analysis and Interpretation (SSIAI)
Show abstract

One of the major steps in visual environment perception for automotive applications is to track keypoints and to subsequently estimate egomotion and environment structure from the trajectories of these keypoints. This paper presents a propagation based tracking method to obtain the 2D trajectories of keypoints from a sequence of images in a monocular camera setup. Instead of relying on the classical RANSAC to obtain accurate keypoint correspondences, we steer the search for keypoint matches by means of propagating the estimated 3D position of the keypoint into the next frame and verifying the photometric consistency. In this process, we continuously predict, estimate and refine the frame-to-frame relative pose which induces the epipolar relation. Experiments on the KITTI dataset as well as on the synthetic COnGRATS dataset show promising results on the estimated courses and accurate keypoint trajectories

Hide abstract

2015

Matthias Ochs, Daniel Biedermann, and Rudolf Mester:
COnGRATS: Realistic Simulation of Traffic Sequences for Autonomous Driving IVCNZ 2015 Image and Vision Computing New Zealand
Show abstract

For evaluating or training different kinds of vision algorithms, a large amount of precise and reliable data is needed. In this paper we present a system to create extended synthetic sequences of traffic environment scenarios, associated with several types of ground truth data. By integrating vehicle dynamics in a configuration tool, and by using path-tracing in an external rendering engine to render the scenes, a system is created that allows ongoing and flexible creation of highly realistic traffic images. For all images, ground truth data is provided for depth, optical flow, surface normals and semantic scene labeling. Sequences that are produced with this system are more varied and closer to natural images than other synthetic datasets before.

Hide abstract

Henry Bradler, Birthe Wiegand, and Rudolf Mester:
The Statistics of Driving Sequences - and what we can learn from them ICCV 2015 Workshop on Computer VIsion for Road Scene Understanding andAutonomous Driving
Show abstract

The motion of a driving car is highly constrained and we claim that powerful predictors can be built that 'learn' the typical egomotion statistics, and support the typical tasks of feature matching, tracking, and egomotion estimation. We analyze the statistics of the 'ground truth' data given in the KITTI odometry benchmark sequences and confirm that a coordinated turn motion model, overlaid by moderate vibrations, is a very realistic model. We develop a predictor that is able to significantly reduce the uncertainty about the relative motion when a new image frame comes in. Such predictors can be used to steer the matching process from frame n to frame n + 1. We show that they can also be employed to detect outliers in the temporal sequence of egomation parameters.

Hide abstract

Nolang Fanani, Marc Barnada, Rudolf Mester:
Motion priors estimation for robust matching initialization in automotive applications International Symposium on Visual Computing (ISVC) 2015, 13-15 December 2015, Las Vegas USA
Show abstract

Tracking keypoints through a video sequence is a crucial first step in the processing chain of many visual SLAM approaches. This paper presents a robust initialization method to provide the initial match for a keypoint tracker, from the 1st frame where a keypoint is detected to the 2nd frame, that is: when no depth information is available. We deal explicitly with the case of long displacements. The starting position is obtained through an optimization that employs a distribution of motion priors based on pyramidal phase correlation, and epipolar geometry constraints. Experiments on the KITTI dataset demonstrate the significant impact of applying a motion prior to the matching. We provide detailed comparisons to the state-of-the-art methods.

Hide abstract

Matthias Ochs, Henry Bradler, and Rudolf Mester:
Enhanced Phase Correlation for reliable and robust estimation of multiple motion distributions Pacific Rim Symposium on Image and Video Technology 23-27 November, 2015, Auckland, New Zealand
Show abstract

Phase correlation is one of the classic methods for sparse mo- tion or displacement estimation. It is renowned in the literature for high precision and insensitivity against illumination variations. We propose several important enhancements to the phase correlation (PhC) method which render it more robust against those situations where a motion measurement is not possible (low structure, too much noise, too di er- ent image content in the corresponding measurement windows). This allows the method to perform self-diagnosis in adverse situations. Furthermore, we extend the PhC method by a robust scheme for detect- ing and classifying the presence of multiple motions and estimating their uncertainties. Experimental results on the Middlebury Stereo Dataset and on the KITTI Optical Flow Dataset show the potential offered by the enhanced method in contrast to the PhC implementation of OpenCV.

Hide abstract

Peter Pinggera, Uwe Franke, Rudolf Mester:
High-Performance Long Range Obstacle Detection Using Stereo Vision. 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015)
Show abstract

Reliable detection of obstacles at long range is crucial for the timely response to hazards by fast-moving safety-critical platforms like autonomous cars. We present a novel method for the joint detection and localization of distant obstacles using a stereo vision system on a moving platform. The approach is applicable to both static and moving obstacles and pushes the limits of detection performance as well as localization accuracy. The proposed detection algorithm is based on sound statistical tests using local geometric criteria which implicitly consider non-flat ground surfaces. To achieve maximum performance, it operates directly on image data instead of precomputed stereo disparity maps. A careful experimental evaluation on several datasets shows excellent detection performance and localization accuracy up to very large distances, even for small obstacles. We demonstrate a parallel implementation of the proposed system on a GPU that executes at real-time speeds.

Hide abstract

Christian Conrad and Rudolf Mester:
Learning Relative Intensity Differences of Pairs of Cameras.
IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS), Karlsruhe, Germany, August 2015
Show abstract

We present an approach to learn relative photometric differences between pairs of cameras, which have partially overlapping fields of views. This is an important problem, especially in appearance based methods to correspondence estimation or object identification in multi-camera systems where grey values observed by different cameras are processed. We model intensity differences among pairs of cameras by means of a low order polynomial (Gray Value Transfer Function - GVTF ) which represents the characteristic curve of the mapping of grey values si produced by camera Ci to the corresponding grey values sj acquired with camera Cj . While the estimation of the GVTF parameters is straight forward once a set of truly corresponding pairs of grey values is available, the non trivial task in the GVTF estimation process solved in this paper is the extraction of corresponding grey value pairs in the presence of geometric and photometric errors. We also present a temporal GVTF update scheme to adapt to gradual global illumination changes, e.g., due to the change of daylight.

Hide abstract

Mikael Persson, Tommaso Piccini, Michael Felsberg, Rudolf Mester:
Robust Stereo Visual Odometry from Monocular Techniques.
IEEE Intelligent Vehicles Conference, June 2015, Seoul (S.Korea)
Show abstract

Visual odometry is one of the most active topics in computer vision. The automotive industry is particularly interested in this field due to the appeal of achieving a high degree of accuracy with inexpensive sensors such as cameras. The best results on this task are currently achieved by systems based on a calibrated stereo camera rig, whereas monocular systems are generally lagging behind in terms of performance. We hypothesise that this is due to stereo visual odometry being an inherently easier problem, rather than than due to higher quality of the state of the art stereo based algorithms. Under this hypothesis, techniques developed for monocular visual odometry systems would be, in general, more refined and robust since they have to deal with an intrinsically more difficult problem. In this work we present a novel stereo visual odometry system for automotive applications based on advanced monocular techniques. We show that the generalization of these techniques to the stereo case result in a significant improvement of the robustness and accuracy of stereo based visual odometry. We support our claims by the system results on the well known KITTI benchmark, achieving the top rank for visual only systems.

Hide abstract

Marc Barnada, Henry Bradler, Matthias Ochs, Rudolf Mester:
Estimation of Automotive Pitch, Yaw, and Roll using Enhanced Phase Correlation on Multiple Far-field Windows.
IEEE Intelligent Vehicles Conference, June 2015, Seoul (S.Korea)
Show abstract

The online-estimation of yaw, pitch, and roll of a moving vehicle is an important ingredient for systems which estimate egomotion, and 3D structure of the environment in a moving vehicle from video information. We present an approach to estimate these angular changes from monocular visual data, based on the fact that the motion of far distant points is not dependent on translation, but only on the current rotation of the camera. The presented approach does not require features (corners, edges, ...) to be extracted. It allows to estimate in parallel also the illumination changes from frame to frame, and thus allows to largely stabilize the estimation of image correspondences and motion vectors, which are most often central entities needed for computating scene structure, distances, etc. The method is significantly less complex and much faster than a full egomotion computation from features, such as PTAM [6], but it can be used for providing motion priors and reduce search spaces for more complex methods which perform a complete analysis of egomotion and dynamic 3D structure of the scene in which a vehicle moves.

Hide abstract

2014

Tommaso Piccini, Mikael Persson, Klas Nordberg, Michael Felsberg, Rudolf Mester:
Good Edgels To Track: Beating The Aperture Problem With Epipolar Geometry
ECCV 2014, 2nd Workshop for Road Scene Understanding and Autonomous Driving. Sept 2014, Zürich
Show abstract

Friedrich Erbs, Andreas Witte, Timo Scharwaechter, Rudolf Mester, Uwe Franke:
Spider-based Stixel Object Segmentation
IEEE Intelligent Vehicles Symposium, Dearborn, Michigan, USA 2014
Show abstract

Peter Pinggera, David Pfeiffer, Uwe Franke, and Rudolf Mester:
Know Your Limits: Accuracy of Long Range Stereoscopic Object Measurements in Practice
European Computer Vision Conference ECCV 2014, Zurich, September 2014
Show abstract

Modern applications of stereo vision, such as advanced driver assistance systems and autonomous vehicles, require highest precision when determining the location and velocity of potential obstacles. Subpixel disparity accuracy in selected image regions is therefore essential. Evaluation benchmarks for stereo correspondence algorithms, such as the popular Middlebury and KITTI frameworks, provide important reference values regarding dense matching performance, but do not sufficiently treat local sub-pixel matching accuracy. In this paper, we explore this important aspect in detail. We present a comprehensive statistical evaluation of selected state-of-the-art stereo matching approaches on an extensive dataset and establish reference values for the precision limits actually achievable in practice. For a carefully calibrated camera setup under real-world imaging conditions, a consistent error limit of 1/10 pixel is determined. We present guidelines on algorithmic choices derived from theory which turn out to be relevant to achieving this accuracy limit in practice.

Hide abstract

Rudolf Mester and Christian Conrad:
When patches match - a statistical view on matching under illumination variation
International Conference on Pattern Recognition, Stockholm, Sweden, 2014
Show abstract

We discuss matching measures (scores and residuals) for comparing image patches under unknown affine photometric (=intensity) transformations. In contrast to existing methods, we derive a fully symmetric matching measure which reflects the fact that both copies of the signal are affected by measurement errors (?noise?), not only one. As it turns out, this evolves into an eigensystem problem; however a simple direct solution for all entities of interest can be given. We strongly advocate for constraining the estimated gain ratio and the estimated mean value offset to realistic ranges, thus preventing the matching scheme from locking into unrealistic correspondences.

Hide abstract

Rudolf Mester:
Motion Estimation Revisited: an Estimation-Theoretic Approach
In Proc. IEEE Southwest Symposium on Image Analysis & Interpretation (SSIAI), 2014
Show abstract

The present paper analyzes some previously unex- plored aspects of motion estimation that are fundamental both for discrete block matching as well as for differential ?optical flow? approaches a` la Lucas-Kanade. It aims at providing a complete estimation-theoretic approach that makes the assumptions about noisy observations of samples from a continuous signal of a certain class explicit. It turns out that motion estimation is a combination of simultaneously estimating the true underlying continuous signal and optimizing the displacement between two hypothetical copies of this unknown signal. Practical schemes such as the current variants of Lucas-Kanade are just approxi- mations to the fundamental estimation problem identified in the present paper. Derivatives appear as derivatives to the continuous signal representation kernels, not as ad hoc discrete derivative masks. The formulation via an explicit signal space defined by kernels is a precondition for analyzing e.g. the convergence range of iterative displacement estimation procedures, and for systematically chosing preconditioning filters. The paper sets the stage for further in-depth analysis of some fundamental issues that have so far been overlooked or ignored in motion analysis.

Hide abstract

2013

Peter Pinggera, Uwe Franke, Rudolf Mester:
Highly Accurate Depth Estimation for Objects at Large Distances
German Conference on Pattern Recognition, Saarbrücken, Germany, 2013
Show abstract

Abstract:Precise stereo-based depth estimation at large distances is challenging: objects become very small, often exhibit low contrast in the image, and can hardly be separated from the background based on disparity due to measurement noise. In this paper we present an approach that overcomes these problems by combining robust object segmentation and highly accurate depth and motion estimation. The segmentation criterion is formulated as a probabilistic combination of disparity, optical flow and image intensity that is optimized

Hide abstract

Christian Conrad, Matthias Mertz, and Rudolf Mester:
Contour-relaxed Superpixels
Energy Minimization Methods in Computer Vision and Pattern Recognition, August 2013, Lund, Sweden
Show abstract

We propose and evaluate a versatile scheme for image pre-segmentation that generates a partition of the image into a selectable number of patches ('superpixels'), under the constraint of obtaining maximum homogeneity of the 'texture' inside of each patch, and maximum accordance of the contours with both the image content as well as a Gibbs-Markov random field model. In contrast to current state-of-the art approaches to superpixel segmentation, 'homogeneity' does not limit itself to smooth region-internal signals and high feature value similarity between neighboring pixels, but is applicable also to highly textured scenes. The energy functional that is to be maximized for this purpose has only a very small number of design parameters, depending on the particular statistical model used for the images. The capability of the resulting partitions to deform according to the image content can be controlled by a single parameter. We show by means of an extensive comparative experimental evaluation that the compactness-controlled contour-relaxed superpixel method outperforms the state-of-the art superpixel algorithms with respect to boundary recall and undersegmentation error while being faster or on a par with respect to runtime.

Hide abstract

Jens Eisenbach, Matthias Mertz, Christian Conrad, and Rudolf Mester:
Reducing Camera Vibrations and Photometric Changes in Surveillance Video
IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), August 2013, Kraków, Poland
Show abstract

We analyze the consequences of instabilities and fluctuations, such as camera shaking and illumination/exposure changes, on typical surveillance video material and devise a systematic way to compensate these changes as much as possible. The phase correlation method plays a decisive role in the proposed scheme, since it is inherently insensitive to gain and offset changes, as well as insensitive against different linear degradations (due to time- variant motion blur) in subsequent images. We show that the listed variations can be compensated effectively, and the image data can be equilibrated significantly before a temporal change detection and/or a background-based detection is performed. We verify the usefulness of the method by comparative tests with and without stabilization, using the changedetection.net benchmark and several stateof-the-art detections methods.

Hide abstract

Jens Eisenbach, Christian Conrad, and Rudolf Mester:
A temporal scheme for fast learning of image-patch correspondences in realistic multi-camera setups
IEEE Conf. Computer Vision and Pattern Recognition: Workshops, June 2013, Portland, OR
Show abstract

This paper addresses the problem of finding corresponding image patches in multi-camera video streams by means of an unsupervised learning method. We determine patch- to-patch correspondence relations ('correspondence priors') merely using information from a temporal change detection. Correspondence priors are essential for geometric multi-camera calibration, but are useful also for further vision tasks such as object tracking and recognition. Since any change detection method with reasonably performance can be applied, our method can be used as an encapsulated processing module and be integrated into existing systems without major structural changes. The only assumption that is made is that relative orientation of pairs of cameras may be arbitrary, but fixed, and that the observed scene shows visual activity. Experimental results show the applicability of the presented approach in real world scenarios where the camera views show large differences in orientation and position. Furthermore we show that a classic spatial matching pipeline, e.g., based on SIFT will typically fail to determine correspondences in these kinds of scenarios.

CVPR Workshop on Camera Networks and Wide Area Scene Analysis.

Hide abstract

Philipp Koschorrek, Tommaso Piccini, Per Öberg, Michael Felsberg, Lars Nielsen, and Rudolf Mester:
A multi-sensor traffic scene dataset with omnidirectional video
IEEE Conf. Computer Vision and Pattern Recognition: Workshops, June 2013, Portland, OR
Show abstract

The development of vehicles that perceive their environment, in particular those using computer vision, indispensably requires large databases of sensor recordings obtained from real cars driven in realistic traffic situations. These datasets should be time shaped for enabling synchronization of sensor data from different sources. Furthermore, full surround environment perception requires high frame rates of synchronized omnidirectional video data to prevent information loss at any speeds.

This paper describes an experimental setup and software environment for recording such synchronized multi-sensor data streams and storing them in a new open source format. The dataset consists of sequences recorded in various environments from a car equipped with an omnidirectional multi-camera, height sensors, an IMU, a velocity sensor, and a GPS. The software environment for reading these data sets will be provided to the public, together with a collection of long multi-sensor and multi-camera data streams stored in the developed format.

CVPR Workshop on Ground Truth: What is a good dataset.

Hide abstract

Vasileios Zografos, Liam Ellis, and Rudolf Mester:
Discriminative Subspace Clustering
Int. Conf. on Computer Vision and Pattern Recognition (CVPR, 2013)
Show abstract

We present a novel method for clustering data drawn from a union of arbitrary dimensional subspaces, called Discriminative Subspace Clustering (DiSC). DiSC solves the subspace clustering problem by using a quadratic classifier trained from unlabeled data (clustering by classification). We generate labels by exploiting the locality of points from the same subspace and a basic affinity criterion. A number of classifiers are then diversely trained from different partitions of the data, and their results are combined together in an ensemble, in order to obtain the final clustering result. We have tested our method with 4 challenging datasets and compared against 8 state-of-the-art methods from literature. Our results show that DiSC is a very strong performer in both accuracy and robustness, and also of low computational complexity.

Hide abstract

Christian Conrad, and Rudolf Mester:
Learning Multi-View Correspondences via Subspace-Based Temporal Coincidences
In Proc. Scandinavian Conferences on Image Analysis (SCIA, 2013)
Show abstract

In this work we present an approach to automatically learn pixel correspondences between pairs of cameras. We build on the method of Temporal Coincidence analysis (TCA) and extend it from the pure temporal (i.e. single-pixel) to the spatiotemporal domain. Our approach is based on learning a statistical model for local spatiotemporal image patches, determining rare, and expressive events from this model, and matching these events across multiple views. Accumulating multi-image coincidences of such events over time allows to learn the desired geometric and photometric relations. The presented method also works for strongly different viewpoints and camera settings, including substantial rotation, and translation. The only assumption that is made is that the relative orientation of pairs of cameras may be arbitrary, but fixed, and that the observed scene shows visual activity. We show that the proposed method outperforms the single pixel approach to TCA both in terms of learning speed and accuracy.

Hide abstract

2012

Christian Conrad, and Rudolf Mester:
Learning Geometrical Transforms between Multi Camera Views using Canonical Correlation Analysis
In Proc. British Machine Vision Conference (BMVC, 2012)
Show abstract

In this work, we study unsupervised learning of correspondences relations (point-to-point, or point-to-point-set) in binocular video streams. This is useful for low level vision tasks in stereo vision or motion estimation as well as in high level applications like object tracking. In contrast to popular probabilistic methods for unsupervised (feature) learning, often involving rather sophisticated machinery and optimization schemes, we present a sampling-free algorithm based on Canonical Correlation Analysis (CCA), and show how 'correspondence priors' can be determined in closed form. Specifically, given video streams of two views of a scene, our algorithm first determines pixel correspondences on a coarse scale. Subsequently it projects those correspondences to the original resolution. For each point in video channel A, regions of high probability containing the corresponding point in image channel B are determined, thus forming correspondence priors. Such correspondence priors may then be plugged into probabilistic and energy based formulations of specific vision applications. Experimental results show the applicability of the proposed method in very different real world scenarios where the binocular views may be subject to substantial spatial transformations.

Hide abstract

David Dederscheck, Thomas M¸ller and Rudolf Mester:
Illumination Invariance for Driving Scene Optical Flow using Comparagram Preselection
accepted for presentation at the 2012 IEEE Intelligent Vehicles Symposium (IV 2012), June 3-7, 2012, in Alcal· de Henares, Spain.
Show abstract

In the recent years, advanced video sensors have become common in driver assistance, coping with the highly dynamic lighting conditions by nonlinear exposure adjustments. However, many computer vision algorithms are still highly sensitive to the resulting sudden brightness changes. We present a method that is able to estimate the relative intensity transfer function (RITF) between images in a sequence even for moving cameras. The according compensation of the input images can improve the performance of further vision tasks significantly, here demonstrated by results from optical flow. Our method identifies corresponding intensity values from areas in the images where no apparent motion is present. The RITF is then estimated from that data and regularized based on its curvature. Finally, built-in tests reliably flag image pairs with 'adverse conditions' where no compensation could be performed.

Hide abstract

Alvaro Guevara, Christian Conrad, and Rudolf Mester:
Curvature oriented clustering of sparse motion vector fields
In Proc. IEEE Southwest Symposium on Image Analysis & Interpretation (SSIAI)
Show abstract

We present an approach to unveil the underlying structure of dynamic scenes from a sparse set of local flow measurements. We first estimate those measurements at carefully selected locations, and subsequently group them into a finite set of different dense flow field hypotheses. These flow fields are represented as parametric functional models, and the number of flow models (=clusters) is determined by an information-theory based approach. Methodically, the grouping task is a two-step clustering scheme, whose intra-cluster modeling step exploits prior knowledge on real flow fields by enforcing low curvature, and the individual covariance matrices of the sparse local flow measurements are introduced in a principled way. The method has been tested successfully on both stereo and general motion sequences from the standard Middlebury database

Hide abstract

Rudolf Mester
A Bayesian view on matching and motion estimation
In Proc. IEEE Southwest Symposium on Image Analysis & Interpretation (SSIAI)
Show abstract

This paper formulates the problem of estimating motion or geometric transforms between images in a Bayesian manner, stressing the relation between continuous and discrete formulations and emphasizing the necessity to employ stochastic distributions on function spaces

Hide abstract

2011

Rudolf Mester:
Recursive live dense reconstruction: some comments on established and imaginable new approaches.
In Live Dense Reconstruction Workshop, Proc. IEEE ICCV 2011, Barcelona, Spain, November 2011.

Alvaro Guevara, Christian Conrad, and Rudolf Mester:
Boosting segmentation results by contour relaxation
In Proc. IEEE Intern. Conf. on Image Processing (ICIP 2011), pages 1405 ø1408, Brussels, September 2011.

M¸ller, Thomas ; Rabe, Clemens ; Rannacher, Jens ; Franke, Uwe ; Mester, Rudolf:
Illumination-Robust Dense Optical Flow Using Census Signatures .
In: Mester, Rudolf ; Felsberg, Michael (Hrsg.) : Pattern Recognition
(33th DAGM symposium Frankfurt, Germany August 30th-September 2nd, 2011).
Berlin / Heidelberg : Springer Verlag, 2011, S. 236-245. (Lecture Notes in Computer Science (LNCS), Nr. 6835) - ISBN 978-3-642-23122-3

Mester, Rudolf ; Felsberg, Michael (Hrsg.) : Pattern Recognition
(33th DAGM symposium Frankfurt, Germany August 30th-September 2nd, 2011).
Berlin / Heidelberg : Springer Verlag, 2011. (Lecture Notes in Computer Science (LNCS), Nr. 6835) - ISBN 978-3-642-23122-3

Friedrich, Holger:
Applications of Spherical Harmonics in Robot Vision.
Frankfurt am Main, Johann Wolfgang Goethe-Universit?t, Ph.D. Dissertation, 2011. 147 Seiten.
Stichw?rter: spherical harmonics; robot navigation; omnidirectional vision

Conrad, Christian ; Guevara, Alvaro ; Mester, Rudolf:
Learning multi-view correspondences from temporal coincidences.
(2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Colorado Springs, CO, USA, June 20-25, 2011).
2011.

Conrad, Christian ; Guevara, Alvaro ; Mester, Rudolf:
T. Rare Events as a Powerful Cue for Finding Multi-View Correspondences .
(Swedish Symposium on Image Analysis, SSBA 2011, Link?ping, March 2011).
2011.

Mester, Rudolf, Conrad, Christian ; Guevara, Alvaro:
Multichannel Segmentation Using CR: Fast Super-Pixels and Temporal Propagation .
(Scandinavian Conference on Image Analysis, SCIA 2011, Ystad, May 2011 (Springer LNCS series)).
2011.

Guevara, Alvaro ; Mester, Rudolf:
Kernels for Reconstructing Nonideally Sampled Nonbandlimited Signals .
(IEEE Workshop on Statistical Signal Processing, Nice (F), 28-30 June 2011).
2011.

Dederscheck, David ; Lenhart, Christine ; Friedrich, Holger ; Mester, Rudolf:
Running on Optical Rails (submitted to International Journal of Computer Vision IJCV) .
2011.
Stichw?rter:  Optical Rails, view based navigation

Guevara, Alvaro ; Mester, Rudolf:
Wiener crosses borders: interpolation based on second order models .
Proc. SPIE 7870 (Electronic Imaging)
(IS&T/SPIE Electronic Imaging 2011 San Francisco, USA January 23 - 27, 2011).
2011.
Stichw?rter:  Interpolation; MMSE; Wiener
[doi>10.1117/12.871198]

2010

Guevara, Alvaro ; Wolenski, Peter:
Convergence results for a self-dual regularization of convex problems .
Talk or presentation: 10th International Conference on Parametric Optimization and Related Topics (paraoptX) 2010, Karlsruher Institut f¸r Technologie,
Karlsruhe, 23.09.2010
Stichw?rter:  convex and parametric optimization; converegence results; self-dual regularization

Guevara, Alvaro ; Conrad, Christian ; Mester, Rudolf:
Grouping visual objects based on flow structure .
Poster presentation at Bernstein Conference on Computational Neuroscience (BCCN) 2010, Berlin Institute of Technology,
Berlin, 27.09.2010

Conrad, Christian ; Guevara, Alvaro ; Mester, Rudolf:
Learning Temporal Coincidences .
Poster presentation at Bernstein Conference on Computational Neuroscience (BCCN) 2010, Berlin Institute of Technology,
Berlin, 27.09.2010

Mester, Rudolf ; Guevara, Alvaro ; Conrad, Christian ; Friedrich, Holger:
Learning visual motion and structure as latent explanations from huge motion data sets .
Poster presentation at Bernstein Conference on Computational Neuroscience (BCCN) 2010, Berlin Institute of Technology,
Berlin, 27.09.2010

Guevara, Alvaro ; Mester, Rudolf:
Minimum Variance Image Interpolation from Noisy and Aliased Samples .
Proc. SSIAI
(IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) Austin, Texas, USA May 23-25, 2010).
2010.
Stichw?rter:  nonideal sampling; minimum mean square error (MMSE) reconstruction; interpolation

Dederscheck, David ; Zahn, Martin ; Friedrich, Holger ; Mester, Rudolf:
Optical Rails: Slicing the View .
Poster presentation at Omnivis Workshop 2010 in conjunction with "Robotics: Science and Systems",
Zaragoza, Spain, 27.06.2010
Stichw?rter:  Optical Rails; occlusion-aware view-based navigation

Dederscheck, David ; Zahn, Martin ; Friedrich, Holger ; Mester, Rudolf:
Optical Rails: View-Based Track Following with Hemispherical Environment Model and Orientation View Descriptors .
(20th International Conference on Pattern Recognition ICPR 2010 Istanbul, Turkey August 23-26, 2010).
2010.

Guevara, Alvaro ; Mester, Rudolf:
Optimal reconstruction from samples for continuous and discrete signals: an statistical approach .
Poster presentation at DAGStat 2010, Technische Universit?t Dortmund, Germany,
Dortmund, 24.03.2010

F¸rtig, Andreas ; Friedrich, Holger ; Mester, Rudolf:
Robust Pixel Classification for RoboCup .
ZBS e.V.
(16. Workshop Farbbildverarbeitung Applikationszentrum (APZ) Ilmenau, Germany October 7-8, 2010).
2010. - ISBN 978-3-00-032504-5
Stichw?rter:  pixel based classification; image statistics

Guevara, Alvaro ; Mester, Rudolf:
Signal Reconstriction from Noisy, Aliased, and Nonideal Samples: What Linear MMSE Approaches Can Achieve .
(2010 European Signal Processing Conference EUSIPCO-2010 Aalborg, Denmark August 23-27, 2010).
2010, S. 1291-1295.

Dederscheck, David ; Zahn, Martin ; Friedrich, Holger ; Mester, Rudolf:
Slicing the View: Occlusion-Aware View-Based Robot Navigation .
In: Goesele, Michael ; Roth, Stefan ; Kuijper, Arjan ; Schiele, Bernt ; Schindler, Konrad (Hrsg.) : Pattern Recognition
(32th DAGM symposium Darmstadt, Germany September 22-24, 2010).
Berlin / Heidelberg : Springer Verlag, 2010, S. 111-120. (Lecture Notes in Computer Science (LNCS), Nr. 6376) - ISBN 978-3-642-15985-5
Stichw?rter:  Optical Rails; occlusion-aware view-based navigation

2009

Dederscheck, David ; Friedrich, Holger ; Lenhart, Christine ; Zahn, Martin ; Mester, Rudolf:
'Featuring' Optical Rails: View-Based Robot Guidance Using Orientation Features on the Sphere .
2009 IEEE 12th International Conference on Computer Vision Workshops
(9th IEEE Workshop on Omnidirectional Vision, Camera Networks and Non-classical Cameras (OMNIVIS2009) Kyoto, Japan 04.10.2009).
IEEE Computer Society Press, 2009, S. 2156-2163. - ISBN 9781424444427 (book) 9781424444410 (dvd)
Stichw?rter:  Optical Rails, robot navigation, spherical harmonics, view based
[doi>10.1109/ICCVW.2009.5457547]

2008

Kondermann, Claudia ; Mester, Rudolf ; Garbe, Christoph:
A Statistical Confidence Measure for Optical Flows .
In: Forsyth, David ; Torr, Philip ; Zisserman, Andrew (Hrsg.) : Computer Vision - ECCV 2008
(The 10th European Conference on Computer Vision (ECCV 2008) Marseille October 12-18, 2008).
Springer Verlag, 2008. (Lecture Notes in Computer Science (LNCS), Nr. 5302-5305)

Wedel, Andreas ; Franke, Uwe ; Badino, Hern·n ; Cremers, Daniel:
B-Spline Modeling of Road Surfaces for Freespace Estimation .
IEEE Intelligent Vehicles Symposium (to appear)
(IEEE Intelligent Vehicles Symposium Einhoven, The Netherlands June 4-6, 2008).
2008.

Preusser, T. ; Scharr, Hanno ; Krajsek, Kai ; Kirby, R. M.:
Building blocks for computer vision with stochastic partial differential equations .
In: International Journal of Computer Vision (IJCV) 80 (2008), Nr. 3, S. 375 - 405

Vaudrey, Tobi ; Badino, Hern·n ; Gehrig, Stefan:
Integrating Disparity Images by Incorporating Disparity Rate .
Second Workshop Robot Vision
(Second Workshop Robot Vision Auckland, New Zealand February 2008).
2008.

Garbe, Christoph S. ; Krajsek, Kai ; Pavlov, Pavel ; Andres, Bj?rn ; M¸hlich, Matthias ; Stuke, Ingo ; Mota, Cicero ; B?hme, Martin ; Haker, Martin ; Schuchert, Tobias ; Scharr, Hanno ; Aach, Til ; Barth, Erhardt ; Mester, Rudolf ; J?hne, Bernd:
Nonlinear analysis of multi-dimensional signals: local adaptive estimation of complex motion and orientation patterns .
In: Dahlhaus, Rainer ; Kurths, J¸rgen ; Maass, Peter ; Timmer, Jens (Hrsg.) : Mathematical Methods in Time Series Analysis and Digital Image Processing.
Berlin Heidelberg : Springer, 2008, (Understanding Complex Systems), S. 231-288. - ISBN 978-3-540-75631-6. ISSN 1860-0832

Friedrich, Holger ; Dederscheck, David ; Rosert, Eduard ; Mester, Rudolf:
Optical Rails. View-based Point-To-Point Navigation using Spherical Harmonics .
In: Rigoll, Gerhard (Hrsg.) : Pattern Recognition
(30th DAGM Symposium M¸nchen 10.-13. Juni 2008).
Berlin : Springer Verlag, 2008, S. 345-354. (Lecture Notes in Computer Science (LNCS), Nr. 5096) - ISBN 978-3-540-69320-8
Stichw?rter:  view based navigation; spherical harmonics

Krajsek, Kai ; Menzel, M. ; Zwanger, M. ; Scharr, Hanno:
Riemannian Anisotropic Diffusion for Tensor Valued Images. .
In: Forsyth, D. ; Torr, P. ; Zisserman, A. (Hrsg.) : Computer Vision - ECCV 2008
(ECCV 2008 Marseille, France October 12-18, 2008).
Berlin : Springer, 2008, S. 326-339. (Lecture Notes in Computer Science (LNCS) Bd. 5305)

Dederscheck, David ; Friedrich, Holger ; Lenhart, Christine ; Penc, Joachim ; Rosert, Eduard ; Scherer, Maximilian ; Mester, Rudolf:
Running on Optical Rails: Theory, Implementation and Testing of Omnidirectional View-based Point-To-Point Navigation .Version: 29.09 2008.  http://hal.inria.fr/inria-00325385/en/.
- Online Ressource,  - The 8th Workshop on Omnidirectional Vision, Camera Networks and Non-classical Cameras - OMNIVIS - INRIA a CCSD electronic archive server based on P.A.O.L (France)
Stichw?rter:  Optical Rails, robot navigation, spherical harmonics, view based

Krajsek, Kai ; Mester, Rudolf ; Scharr, Hanno:
Statistically Optimal Averaging for Image Restoration and Optical Flow Estimation .
In: Rigoll, Gerhard (Hrsg.) : Pattern Recognition
(30th DAGM Symposium M¸nchen 10.-13. Juni 2008).
Berlin : Springer Verlag, 2008, S. 466-475. (Lecture Notes in Computer Science, Nr. 5096)
Stichw?rter:  recipient of DAGM price 2008

Badino, Hern·n ; Vaudrey, Tobi ; Franke, Uwe ; Mester, Rudolf:
Stereo-based Free Space Computation in Complex Traffic Scenarios .
Southwest Symposium on Image Analysis and Interpretation
(Southwest Symposium on Image Analysis and Interpretation Santa Fe, New Mexico, USA March 2008).
2008.

Franke, Uwe ; Gehrig, Stefan ; Badino, Hern·n ; Rabe, Clemens:
Towards Optimal Stereo Analysis of Image Sequences .
Second Workshop Robot Vision
(Second Workshop Robot Vision Auckland, New Zealand February 2008).
2008.

Friedrich, Holger ; Dederscheck, David ; Rosert, Eduard ; Mester, Rudolf:
View-based navigation using spherical harmonics and 'optical rails' .
In: Swedish Society for Automated Image Analysis (Veranst.):
Proceedings SSBA 2008
(Symposium on Image Analysis Lund, Sweden March 12-14, 2008).
2008, S. 47-50.

Friedrich, Holger ; Dederscheck, David ; Mutz, Martin ; Mester, Rudolf:
View-based Robot Localization Using Illumination-invariant Spherical Harmonics Descriptors .
In: Ranchordas, Alpesh ; Araujo, Helder (Hrsg.) : INSTICC and University of Madeira (Veranst.):
Proceedings of the International Joint Conference on Computer Vision and Computer Graphics Theory and Applications
(3rd International Conference on Computer Vision Theory and Applications (VISAPP/VISGRAPP) Funchal, Madeira, Portugal 22.-25.01.2008). Bd. 2.
2008, S. 543-550. - ISBN 978-989-8111-22-7
Stichw?rter:  robot localization, spherical harmonics, illumination invariance, PCA

2007

Badino, Hern·n:
A Robust Approach for Ego-Motion Estimation Using a Mobile Stereo Platform .
In: J?hne, Bernd ; Mester, Rudolf ; Barth, E. ; Scharr, Hanno (Hrsg.) : Complex Motion
(First International Workshop on Complex Motion (IWCM) G¸nzburg, Germany Oct. 12 - 14, 2004).
Springer Verlag, 2007. (Lecture Notes in Computer Science (LNCS), Nr. 3417) - ISBN 978-3-540-69864-7

Krajsek, Kai ; Mester, Rudolf:
A Unified Theory for Steerable and Quadrature Filters .
In: Braz, J. ; Ranchordas, A. ; Ara˙jo, H. ; Jorge, J. (Hrsg.) : Advances in Computer Graphics and Computer Vision
(International Conferences VISAPP and GRAPP 2006 Set˙bal, Portugal February 25-28, 2006).
Berlin : Springer Verlag, 2007, S. 201-214. - ISBN 978-3-540-75272-1
Stichw?rter:  steerable filters, Lie group theory, LOCOMOTOR

Gehrig, Stefan ; Badino, Hern·n ; Gall, J¸rgen:
Accurate and Model-Free Pose Estimation of Crash Test Dummies .
In: Klette, Reinhard ; Maetxas, Dimitris ; Rosenhahn, Bodo (Hrsg.) : Human Motion - Understanding, Modeling, Capture and Animation.
Springer Verlag, 2007, S. 443-466.

Krajsek, Kai ; Mester, Rudolf:
Bayesian Model Selection for Optical Flow Estimation .
In: Hamprecht, F.A. ; Schn?rr, C. ; J?hne, B. (Hrsg.) : Pattern Recognition
(29th DAGM Symposium Heidelberg September 12th-14th, 2007).
2007, S. 142-151. (Lecture Notes in Computer Science (LNCS), Nr. 4713) - ISBN 978-3-540-74933-2
Stichw?rter:  optical flow

J?hne, B. ; Mester, Rudolf ; Barth, E. ; Scharr, Hanno (Hrsg.):
Complex Motion .
(First International Workshop on Complex Motion (IWCM) G¸nzburg Oct. 12 - 14, 2004)
Springer Verlag, 2007
(Lecture Notes in Computer Science (LNCS), Nr. 3417).
- 235 Seiten. ISBN 978-3-540-69864-7

Badino, Hern·n ; Franke, Uwe ; Mester, Rudolf:
Free Space Computation Using Stochastic Occupancy Grids and Dynamic Programming .
Workshop on Dynamical Vision, ICCV
(International Conference on Computer Vision (ICCV) Rio de Janeiro October 2007).
2007.
Stichw?rter:  stereo; stochastic occupancy grids; Kalman filter; free space analysis

Kominiarczuk, Jakub K. ; Krajsek, Kai ; Mester, Rudolf:
Highly Accurate Orientation Estimation Using Steerable Filters .
Proceedings ICIP 2007 (to appear)
(IEEE International Conference on Image Processing (ICIP 2007) San Antonio, USA September 16th-19th, 2007).
IEEE Computer Society Press, 2007.

Mester, Rudolf:
Statistical certainty models in image processing .
Proceedings of the IEEE/SP 14th Workshop on Statistical Signal Processing
(IEEE/SP 14th Workshop on Statistical Signal Processing Madison, Wisconsin (USA) August 26-29, 2007).
2007, S. 581-585.
[doi>10.1109/SSP.2007.4301325]

Friedrich, Holger ; Dederscheck, David ; Krajsek, Kai ; Mester, Rudolf:
View-based Robot Localization Using Spherical Harmonics: Concept and First Experimental Results .
In: Hamprecht, F.A. ; Schn?rr, C. ; J?hne, B. (Hrsg.) : Pattern Recognition
(29th DAGM Symposium Heidelberg September 12th-14th, 2007).
Berlin : Springer Verlag, 2007, S. 21-31. (Lecture Notes in Computer Science (LNCS), Nr. 4713) - ISBN 978-3-540-74933-2
Stichw?rter:  robot localization, spherical harmonics

Krajsek, Kai ; Mester, Rudolf:
Wiener-optimized discrete filters for differential motion estimation .
In: J?hne, Bernd ; Barth, Erhard ; Mester, Rudolf ; Scharr, Hanno (Hrsg.) : Complex Motion (IWCM04)
(1st International Workshop on Complex Motion (IWCM04) Reisensburg/G¸nzburg, Germany October 12-14).
Heidelberg : Springer Verlag, 2007, S. 30-41. (Lecture Notes in Computer Science (LNCS); http://www.springeronline.com/978-3-540-69864-7 Bd. 3417) - ISBN 978-3-540-69864-7
Stichw?rter:  IWCM; motion estimation; LOCOMOTOR

2006

Krajsek, Kai ; Mester, Rudolf:
A maximum likelihood estimator for choosing the regularization parameters in global optical flow methods .
Proceedings ICIP 2006
(International Conference on Image processing Atlanta 8-11 October).
2006.

M¸hlich, Matthias ; Aach, Til:
A Theory for Multiple Orientation Estimation .
Proc. European Conference on Computer Vision (ECCV)
(European Conference on Computer Vision (ECCV) Graz 2006).
2006.
Stichw?rter:  LOCOMOTOR

Krajsek, Kai ; Mester, Rudolf:
A Unified Theory for Steerable and Quadrature Filters .
Proceedings VISAPP
(VISAPP Set˙bal, Portugal February 25-28, 2006).
2006.
Stichw?rter:  steerable filters, Lie group theory, LOCOMOTOR

Gehrig, Stefan ; Badino, Hern·n ; Payson, Pascal:
Accurate and Model-Free Pose Estimation of Small Objects for Crash Video Analysis .
Proc. British Machine Vision Conference
(BMVC06 Edinburgh, England September).
2006.

Krajsek, Kai ; Mester, Rudolf:
Marginalized maximum a posteriori hyper-parameter estimation for global optical flow techniques .
Proceedings MaxEnt 2006
(26 th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering (MaxEnt 2006) Paris, France July 8-13, 2006).
2006.

Krajsek, Kai ; Mester, Rudolf:
On the equivalence of variational and statistical differential motion estimation .
Proceedings SSIAI 2006
(2006 Southwest Symposium on Image Analysis and Interpretation Denver, Colorado March 26-28, 2006).
2006.
Stichw?rter:  Bayesian motion estimation, LOCOMOTOR

Badino, Hern·n ; Franke, Uwe ; Rabe, Clemens ; Gehrig, Sfefan:
Stereo-vision based detection of moving objects under strong camera motion .
Proceedings of the International Joint Conference on Computer Vision and Computer Graphics Theory and Applications
(International Conference on Computer Vision Theory and Applications Setubal, Portugal February).
2006.

Krajsek, Kai ; Mester, Rudolf:
The Edge Preserving Wiener Filter for Scalar and Tensor Valued Images .
In: Franke, Katrin ; M¸ller, Klaus-Robert ; Nickolay, Bertram ; Sch?fer, Ralf (Hrsg.) : Pattern Recognition
(28th DAGM Symposium Berlin 12.-14. September 2006).
Berlin : Springer, 2006, S. 91-100. (Lecture Notes in Computer Science (LNCS) Bd. 4174)
Stichw?rter:  Wiener filter; edge preserving filtering; LOCOMOTOR

2005

Franke, Uwe ; Rabe, Clemens ; Badino, Hern·n ; Gehrig, Sfefan:
6D-Vision: Fusion of Stereo and Motion for Robust Environment Perception .
In: Kropatsch, Walter ; Sablatnig, Robert ; Hanbury, Allan (Hrsg.) : Pattern Recognition
(27th DAGM Symposium Vienna, Austria August 31th - September 2nd, 2005).
Springer Verlag, 2005. (Lecture Notes in Computer Science (LNCS), Nr. 3663)

M¸hlich, Matthias ; Mester, Rudolf:
A fast algorithm for statistically optimized orientation estimation .
In: Kropatsch, Walter ; Sablatnig, Robert ; Hanbury, Allan (Hrsg.) : Pattern Recognition 2005
(DAGM 2005 - 27th Annual meeting of the German Association for Pattern Recognition Vienna, Austria August 31th - September 2nd, 2005).
Heidelberg : Springer Verlag, 2005, S. 238-245. (Lecture Notes in Computer Science Bd. 3663)
Stichw?rter:  orientation estimation; structure tensor; total least squares; equilibration, LOCOMOTOR

Mester, Rudolf:
Editorial .
In: Signal Processing: Image Communication: Special Issue on Advanced Aspects of Motion Estimation 20 (2005), Nr. 6, S. 503-509

M¸hlich, Matthias:
Estimation in Projective Spaces and Applications in Computer Vision .
Frankfurt : ?, 2005.
Zugl.: Frankfurt am Main, Johann Wolfgang Goethe-Universit?t, Ph.D. Dissertation, 2005.
- 203 Seiten.
Stichw?rter:  orientation estimation; structure tensor; total least squares; equilibration

M¸hlich, Matthias ; Mester, Rudolf:
Optimal Estimation of Homogeneous Vectors .
Proc. SCIA 2005
(Scandinavian Conference on Image Analysis 2005 Joensuu, Finland July 2005).
Heidelberg : Springer, 2005.
Stichw?rter:  Homogeneous Vectors, Estimation Theory, LOCOMOTOR

Krajsek, Kai ; Mester, Rudolf:
Signal and noise adapted filters for differential motion estimation .
In: Kropatsch, Walter ; Sablatnig, Robert ; Hanbury, Allan (Hrsg.) : Pattern Recognition 2005
(DAGM 2005 - 27th Annual meeting of the German Association for Pattern Recognition Vienna, Austria August 30th - September 2nd, 2005).
Heidelberg : Springer Verlag, 2005, S. 476-484. (Lecture Notes in Computer Science Bd. 3663)
Stichw?rter:  motion estimation; filter design, LOCOMOTOR

Mester, Rudolf (Hrsg.):
Special Issue on Advanced Aspects of Motion Estimation .
Amsterdam : Elsevier, 2005
(Signal Processing: Image Communication Bd. 20, Nr. 6).
- 90 Seiten. ISSN 0923-5965

M¸hlich, Matthias:
Subspace Estimation with Uncertain and Correlated Data .
In: Klette, Reinhard ; Kozera, Ryszard ; Noakes, Lyle ; Weickert, Joachim (Hrsg.) : Geometric Properties from Incomplete Data
(Geometric Properties from Incomplete Data Dagstuhl 21.03.-26.03.04).
Dordrecht, Boston, London : Kluwer, 2005, S. 355-374.
Stichw?rter:  Subspace Estimation, LOCOMOTOR

2004

M¸hlich, Matthias ; Mester, Rudolf:
A Statistical Extension of Normalized Convolution and its Usage for Image Interpolation and Filtering .
EUSIPCO-2004 Proceedings (in print)
(12th European Signal Processing Conference (Eusipco) Vienna, Austria September 6-10, 2004).
2004.
Stichw?rter:  LOCOMOTOR

M¸hlich, Matthias ; Mester, Rudolf:
A statistical unification of image interpolation, error concealment, and source-adapted filter design .
In: IEEE Computer Society (Hrsg.) : Image Analysis and Interpretation, 2004
(6th IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI '04) Lake Tahoe, USA 28-30 March 2004).
Los Alamitos : IEEE Computer Society Press, 2004, S. 128-132. - ISBN 0-7803-8387-7
Stichw?rter:  LOCOMOTOR

Mester, Rudolf:
Special Session on the Convergence of Computer Vision and Visual Communication .
In: van den Schaar, Michaela (Hrsg.) : Proceedings PCS 2004
(Picture Coding Symposium 2004 San Francisco December 2004).
2004.

Comaniciu, D. ; Kanatani, K. ; Mester, Rudolf (Hrsg.):
Statistical Methods in Video Processing .
(ECCV 2004 Workshop SMVP 2004 Prague, Czech Republic May 16, 2004)
Bd. 3247. Berlin : Springer, 2004.
- 199 Seiten. ISBN 3-540-23989-8
Stichw?rter:  3D scene reconstruction, 3D shape inference, computational geometry, computer vision , image processing, image sequences, multi-body motion segmentation, probabilistic tracking

Mester, Rudolf:
Towards a unified theory of motion estimation: bridging the gap between differential and matching approaches .
In: van den Schaar, Michaela (Hrsg.) : Proceedings PCS 2004
(Picture Coding Symposium 2004 San Francisco December 2004).
2004.

M¸hlich, Matthias ; Mester, Rudolf:
Unbiased Errors-In-Variables Estimation Using Generalized Eigensystem Analysis .
In: Comaniciu, Dorin ; Kanatani, Kenichi ; Mester, Rudolf ; Suter, David (Hrsg.) : Statistical Methods in Video Processing
(2nd Workshop on Statistical Methods in Video Processing (SMVP) during the 8th European Conference on Computer Vision (ECCV) Prague, Czech Republic May 11-14, 2004).
Berlin : Springer Verlag, 2004, S. 38-49. (Lecture Notes in Computer Science Bd. 3247) - ISBN 3-540-23989-8
Stichw?rter:  LOCOMOTOR

2003

Mester, Rudolf:
A new view at differential and tensor-based motion estimation schemes .
In: Michaelis, B. ; Krell, G. (Hrsg.) : Pattern Recognition 2003
(25th annual conference of the Deutsche Arbeitsgemeinschaft f¸r Mustererkennung (DAGM) Magdeburg 10.-12. September 2003).
Heidelberg : Springer Verlag, 2003, S. 321-329. (Lecture Notes in Computer Science (LNCS) Bd. 2781) - ISBN 3-540-40861-4
Stichw?rter:  LOCOMOTOR

Aach, T. ; Toth, D. ; Mester, Rudolf:
Motion estimation in varying illumination using a Total Least Squares distance measure .
Proceedings PCS 2003
(Picture Coding Symposium 2003 Saint-Malo, France April 23-25, 2003).
2003.
Stichw?rter:  LOCOMOTOR

Mester, Rudolf:
On the mathematical structure of direction and motion estimation .
Proceedings Physics in Signal and Image Processing
(3rd International Symposium on Physics in Signal and Image Processing (PSIP) Grenoble, France January 29-31, 2003).
2003, S. 129-132.
Stichw?rter:  LOCOMOTOR

Mester, Rudolf:
Special session on Advanced Methods for Motion Analysis .
(IEEE International Conference on Image Processing (ICIP 2003) Barcelona, Spain September 2003).
2003.
Stichw?rter:  LOCOMOTOR

Mester, Rudolf:
The generalization, optimization and information-theoretic justification of filter-based and autocovariance-based motion estimation .
In: IEEE Computer Society Press (Hrsg.) : Proceedings ICIP 2003
(IEEE International Conference on Image Processing (ICIP) Barcelona, Spain September 14-17, 2003).
2003, S. III-81-4. - ISBN 0-7803-7751-6
Stichw?rter:  LOCOMOTOR

until 2003

Mester, Rudolf:
A system-theoretical view on local motion estimation .
In: IEEE standard office (Hrsg.) : 45th Midwest Symposium on Circuits and Systems
(IEEE Southwest Symposium on Image Analysis and Interpretation Santa Fe, USA April 2002).
IEEE Computer Society Press, 2002, S. 201 - 205. - ISBN 0-7695-1537-1
Stichw?rter:  LOCOMOTOR

Mester, Rudolf:
Some steps towards a unified motion estimation procedure .
(45th IEEE MidWest Symposium on Circuits and Systems (MWSCAS) Tulsa, Oklahoma August 4-7, 2002).
2002.
Stichw?rter:  LOCOMOTOR

M¸hlich, Matthias ; Mester, Rudolf:
A considerable improvement in non-iterative homography estimation using TLS and equilibration .
In: Pattern Recognition Letters 22 (2001), Nr. 11, S. 1181-1189

Aach, T. ; Mester, Rudolf:
Bayesian Illumination-invariant Change Detection using a Total Least Squares Test Statistic .
(Colloque GRETSI 2001 Toulouse, France September 2001).
2001.

Aach, T. ; D¸mbgen, L. ; Toth, D. ; Mester, Rudolf:
Bayesian Illumination-invariant Motion Detection .
In: IEEE Computer Society Press (Hrsg.) : Proceedings of the 2001 International Conference on Image Processing
(IEEE Signal Processing Society 2001 International Conference on Image Processing Thessaloniki, Greece October 7-10, 2001).
2001.

Mester, Rudolf ; Aach, T. ; D¸mbgen, L.:
Illumination-invariant change detection using a statistical colinearity criterion .
In: Radig, B. ; Florczyk, S. (Hrsg.) : Pattern Recognition: Proceedings 23rd DAGM Symposium
(Pattern Recognition: Proceedings 23rd DAGM Symposium M¸nchen September 12-14, 2001).
Springer Verlag, 2001, S. 170-177. (Lecture Notes in Computer Science Bd. 2191) - ISBN 3-540-42596-9

Mester, Rudolf ; M¸hlich, Matthias:
Improving Motion and Orientation Estimation Using an Equilibrated Total Least Squares Approach .
In: IEEE Computer Society Press (Hrsg.) : Proceedings of the 2001 International Conference on Image Processing
(IEEE International Conference on Image Processing (ICIP) Thessaloniki, Greece October 7-10, 2001).
2001, S. 640-643.

M¸hlich, Matthias ; Mester, Rudolf:
Subspace Methods and Equilibration in Computer Vision .
In: Austvoll, I. (Hrsg.) : Proceedings of the 12th Scandinavian Conference on Image Analysis
(Scandinavian Conference on Image Analysis Bergen, Norwegen Juni 2001).
Stavanger, Norwegen : NOBIM, 2001.

Mester, Rudolf:
Orientation estimation: conventional techniques and a new non-differential method .
(European Signal Processing Conference (EUSIPCO'2000) Tampere, Finnland September 2000).
2000.

M¸hlich, Matthias ; Mester, Rudolf:
A Note on Error Metrics and Optimization Criteria in 3D Vision .
In: Girod ; Niemann ; Seidel (Hrsg.) : Proc. IEEE Intern. Workshop on Vision, Modeling, and Visualization
(IEEE Intern. Workshop on Vision, Modeling, and Visualization Erlangen, Germany November 1999).
St. Augustin : Infix, 1999, S. 149-156.

Trautwein, S. ; M¸hlich, Matthias ; Mester, Rudolf:
Estimating Consistent Motion From Three Views: An Alternative To Trifocal Analysis .
In: Solina, Franc ; Leonardis, Ales (Hrsg.) : Proceedings of Computer Analysis of Images and Patterns (CAIP'99)
(Computer Analysis of Images and Patterns (CAIP'99) Ljubljana (Slowenien) September 1999).
Springer, 1999, S. 311-320. (Lecture Notes on Computer Science (LNCS) Bd. 1689)

Feiden, Dirk ; M¸hlich, Matthias ; Mester, Rudolf:
Robuste Bewegungssch?tzung aus monokularen Bildsequenzen von planaren Welten .
In: F?rstner, W. ; Buhmann, W. (Hrsg.) : Mustererkennung 1999
(21. DAGM-Symposium Bonn September 1999).
Springer Verlag, 1999, S. 349-356. (Informatik aktuell)

M¸hlich, Matthias ; Mester, Rudolf:
Ein verallgemeinerter Total Least Squares Ansatz zur Sch?tzung der Epipolargeometrie .
In: Levi ; Ahlers ; May (Hrsg.) : Mustererkennung 1998
(Jahrestagung der Dt. Arbeitsgemeinschaft f¸r Mustererkennung (DAGM'98) Stuttgart September 1998).
Springer Verlag, 1998, S. 349-356.

M¸hlich, Matthias ; Mester, Rudolf:
The Role of Total Least Squares in Motion Analysis .
In: Burkhardt ; Neumann (Hrsg.) : Proc. European Conference on Computer Vision (ECCV)
(European Conference on Computer Vision (ECCV) Freiburg Juni 1998).
Springer Verlag, 1998, S. 305-321. (Lecture Notes on Computer Science Bd. 1407)

Mester, Rudolf:
Stabilit?ts- und Zuverl?ssigkeitsaspekte im Zusammenhang mit dem Structure from Motion Problem .
(Jahrestagung der Deutschen Gesellschaft f¸r Photogrammetrie und Fernerkundung (DGPF) 1997 Frankfurt am Main September 1997).
1997.

Mester, Rudolf:
Stochastische Modelle und Methoden in der Bildsequenzanalyse .
In: Hill, B. (Hrsg.) : Proc. Aachener Symposium zur Signaltheorie¥97
(Aachener Symposium zur Signaltheorie¥97 Aachen M?rz 1997).
1997.

H?tter, M. ; Mester, Rudolf ; M¸ller, F.:
Detection and description of moving objects by stochastic modelling and analysis of complex scenes .
In: Signal Processing: Image Communication 8 (1996), S. 281-293

H?tter, M. ; Mester, Rudolf ; Meyer, M.:
Detection of Moving Objects Using a Robust Displacement Estimation Including a Statistical Error Analysis .
(13th International Conference on Pattern Recognition Wien August 1996). Bd. IV.
1996, S. 249-255.

H?tter, M. ; Mester, Rudolf ; M¸ller, F.:
Moving Object Detection in Image Sequences using Texture Features .
Proc. 5th International Workshop on Time-varying Image Processing and Moving Object Recognition
(5th International Workshop on Time-varying Image Processing and Moving Object Recognition Florenz September 1996).
1996.

Mester, Rudolf ; H?tter, M. ; P?chm¸ller, W.:
Umwelterfassung mit bewegten Kameras .
In: Mertsching, B?rbel (Hrsg.) : Aktives Sehen in technischen und biologischen Systemen
(Workshop der GI-Fachgruppe 1.0.4 Bildverstehen Hamburg Dezember 1996).
1996, S. 117-126. (Proceedings in Artificial Intelligence)

H?tter, M. ; Mester, Rudolf ; Meyer, M.:
Detection of Moving Objects in Natural Scenes by a Stochastic Multi-Feature Analysis of Video Sequences .
(29th Annual 1995 International IEEE Carnahan Conference on Security Technology Sanderstead, Surrey, England Oktober 1995).
1995, S. 47-52.

Aach, T. ; Kaup, A. ; Mester, Rudolf:
On texture analysis: Local energy transforms versus quadrature filters .
In: Signal Processing 45 (1995), Nr. 2, S. 173-182

Mester, Rudolf ; H?tter, M.:
Robust displacement vector estimation including a statistical error analysis .
Proc. 5th International Conference on Image Processing and its Applications
(5th International Conference on Image Processing and its Applications Edinburgh, UK).
London : Institution of Electrical Engineers (IEE), 1995, S. 168-172.

Mester, Rudolf ; H?tter, M.:
Zuverl?ssigkeit und Effizienz von Verfahren zur Verschiebungsvektorsch?tzung .
In: Sagerer ; Posch ; Kummert (Hrsg.) : Mustererkennung
(17. DAGM Symposium Bielefeld September 1995).
Springer Verlag, 1995, S. 285-294. (Informatik aktuell)

Aach, T. ; Kaup, A. ; Mester, Rudolf:
Change detection in image sequences using Gibbs random fields: a Bayesian approach .
(IEEE Workshop Intelligent Signal Processing and Communications Systems Sendai, Japan Oktober 1993).
1993.

Aach, T. ; Kaup, A. ; Mester, Rudolf:
Statistical model-based change detection in moving video .
In: Signal Processing 31 (1993), Nr. 2, S. 165-180

Mester, Rudolf ; Franke, U.:
Spectral entropy-activity classification in adaptive transform coding .
In: IEEE Journal on Selected Areas in Communications 10 (1992), Nr. 5, S. 913-917

Aach, T. ; Kaup, A. ; Mester, Rudolf:
A statistical framework for change detection in image sequences .
Proc. 13th GRETSI
(Symposium on signal and image processing Juan-Les-Pins September 1991).
1991, S. 1149-1152.

Mester, Rudolf ; Aach, T. ; Franke, U.:
Image segmentation experiments using the contour relaxation algorithm .
In: Zeitschrift f¸r Photogrammetrie und Fernerkundung (1991), Nr. 4, S. 127-132

Aach, T. ; Kaup, A. ; Mester, Rudolf:
Combined displacement estimation and segmentation of stereo image pairs based on Gibbs random fields .
Proceedings ICASSP '90
(Intern. Conference on Acoustics, Speech, and Signal Processing ICASSP'90 Albuquerque April 1990).
1990, S. 2301-2304.

Aach, T. ; Dawid, H. ; Mester, Rudolf:
3D-Segmentierung von Kernspintomogrammen unter Verwendung eines stochastischen Objektformmodells .
In: Giani, G. ; Repges, R. (Hrsg.) : Medizinische Informatik und Statistik 71
(Jahrestagung der Gesellschaft f¸r Medizinische Datenverarbeitung und Statistik (GMDS) Aachen September 1989).
Springer Verlag, 1989, S. 306-309.

Mester, Rudolf ; Franke, U. ; Aach, T.:
Fortschritte in der Modellierung nat¸rlicher Bilder .
In: ITG Fachbericht 107 "Stochastische Modelle und Methoden in der Informationstechnik" (1989), S. 29-34

Mester, Rudolf:
Regionenorientierte Bildsegmentierung unter Verwendung stochastischer Bildmodelle .
D¸sseldorf : VDI Verlag, 1989
(VDI Fortschrittberichte Bd. 10, Nr. 106).
Zugl.: Aachen, Fakult?t f¸r Elektrotechnik, RWTH, Ph.D. Dissertation, 1988

Aach, T. ; Mester, Rudolf ; Franke, U.:
Top-down image segmentation using object detection and contour relaxation .
Proceedings ICASSP 1989
(Intern. Conference on Acoustics, Speech, and Signal Processing ICASSP'89 Glasgow Mai 1989).
1989, S. 1703-1706.

Franke, U. ; Mester, Rudolf ; Aach, T.:
Constrained iterative restoration techniques: A powerful tool in region based texture coding .
In: Lacoume, J. L. et al. (Hrsg.) : Signal Processing IV: Theories and Applications
(European Signal Processing Conference EUSIPCO-88 Grenoble, France September 1988).
Elsevier, 1988, S. 1145-1148.

Aach, T. ; Mester, Rudolf ; Franke, U.:
From texture energy measures to quadrature filter pairs - A system theoretical view of texture feature extraction .
In: Lacoume, J. L. et al. (Hrsg.) : Signal Processing IV: Theories and Applications
(European Signal Processing Conference EUSIPCO-88 Grenoble, France September 1988).
Elsevier, 1988, S. 827-830.

Mester, Rudolf ; Franke, U.:
Image segmentation on the basis of statistical models for region oriented image coding .
(Picture Coding Symposium 88 Turin September 1988).
1988.

Mester, Rudolf ; Franke, U. ; Aach, T.:
Image segmentation using likelihood ratio tests and Markov region shape models .
In: Lacoume, J. L. et al. (Hrsg.) : Signal Processing IV: Theories and Applications
(European Signal Processing Conference EUSIPCO-88 Grenoble, France September 1988).
Elsevier, 1988, S. 837-840.

Franke, U. ; Mester, Rudolf:
Region based image representation with variable contour and texture reconstruction quality .
In: Hsing, T. R. (Hrsg.) : Proc. SPIE 1988
(Cambridge Symposium on Visual Communications and Image Processing 88 Cambridge/Mass. November 1988).
1988, S. 178-186.

Franke, U. ; Mester, Rudolf:
Representation of the texture signals in region-based image coding schemes: A comparative study .
(Picture Coding Symposium 88 Turin September 1988).
1988.

Mester, Rudolf ; Franke, U. ; Aach, T.:
Segmentation of image pairs and sequences by contour relaxation .
In: Bunke, H. et al. (Hrsg.) : Erschienen in Informatik Fachberichte 180
(DAGM Symposium Mustererkennung Z¸rich September 1988).
Springer Verlag, 1988, S. 104-110.

Mester, Rudolf ; Franke, U.:
Statistical model based image segmentation using region growing, contour relaxation and classification .
In: Hsing, T. R. (Hrsg.) : Proc. SPIE 1988
(Cambridge Symposium on Visual Communications and Image Processing 88 Cambridge/Mass. November 1988).
1988, S. 616-624.




This page was extracted from the UnivIS database (21-Feb-2011, 13:56:57).