Motion Segmentation by Learning Homography Matrices from Motor Signals

—Motion information is an important cue for a robot to separate foreground moving objects from the static background world. Based on the observation that the motion of the background (from the robot’s egocentric view) has stronger correlation to the robot’s motor signals than the motion of foreground objects, we propose a novel method to detect foreground moving objects by clustering image features according to their motion consistency with motor signals. Corner/edge features are detected and tracked across adjacent frames. The errors between the estimated feature locations based on motor signals and their actual tracked locations are calculated. The features are clustered into background/foreground using Expectation-Maximization on these errors. Labeled features are then used for pixel-level image segmentation with the Active Contours and Graph-based Transduction techniques. Unlike pixel-level background subtraction methods, the proposed approach does not require a large number ...

• Type: Journal
• Year: 2011
• Where: CRV
• Authors: Changhai Xu, Jingen Liu, Benjamin Kuipers
• Keywords: CRV 2011, Foreground Background, Foreground Objects, Motion Segmentation, Robotics