Learning General Optical Flow Subspaces for Egomotion Estimation and Detection of Motion Anomalies

This paper deals with estimation of dense optical flow and ego-motion in a generalized imaging system by exploiting probabilistic linear subspace constraints on the flow. We deal with the extended motion of the imaging system through an environment that we assume to have some degree of statistical regularity. For example, in autonomous ground vehicles the structure of the environment around the vehicle is far from arbitrary, and the depth at each pixel is often approximately constant. The subspace constraints hold not only for perspective cameras, but in fact for a very general class of imaging systems, including catadioptric and multiple-view systems. Using minimal assumptions about the imaging system, we learn a probabilistic subspace constraint that captures the statistical regularity of the scene geometry relative to an imaging system. We propose an extension to probabilistic PCA (Tipping and Bishop, 1999) as a way to robustly learn this subspace from recorded imag...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Richard Roberts (Georgia Institute of Technology), Christian Potthast (Georgia Institute of Technology), Frank Dellaert (Georgia Institute of Technology)
• Keywords: Computer Vision, CVPR 2009, Detection Of Motion Anomalies, Egomotion Estimation, General Optical Flow