Computational efficient methods for egomotion estimation

Estimation of Automotive Pitch, Yaw and Roll

Motion on far-field windows is influenced mostly by rotations and not by translation. In this paper, we determined the translation of several windows of the images to then robustly estimate the global 2D displacement and the rotation angles. The estimation of the rotation matrix is used in our current research for determining the motion priors of several keypoints and to track keypoints and edge pixels.

The pipeline of the proposed method uses several checks to auto-diagnose problematic cases and flag those situations where no reliable measurements can be achieved.

System overview

Exemplary results (KITTI seq 03)

Detailed presentation

Find a detailed presentation about the estimation of automotive Pitch, Yaw, and Roll using Enhanced Phase Correlation on Multiple Far-field Windows: here


  • M. Barnada, C. Conrad, H. Bradler, M. Ochs and R. Mester: Estimation of automotive pitch, yaw, and roll using enhanced phase correlation on multiple far-field windows. Intelligent Vehicles Symposium (IV), Seoul ,South Korea, June 2015
  • M. Ochs, H. Bradler and R. Mester: Enhanced Phase Correlation for Reliable and Robust Estimation of Multiple Motion Distributions. Pacific Rim Symposium on Image and Video Technology (PSIVT), Auckland, New Zealand, November 2015


Learning, Adaptive, and Biology-Inspired Systems
COnGRATS: COmputer GRAphic generated synthetic Traffic Scenes