Skip to Main Content
This paper presents a real-time system for moving object and obstacle detection (MOOD) based on stereo vision. A disparity map is calculated to have a 3D representation of the scene and to recognize obstacles. The best methods in literature have been employed and opportunely modified to obtain the best compromise between the high frame-rate and the high accuracy requirements. An efficient algorithm for motion vector analysis, based on optical flow, is used to segment moving objects and obstacles. The application domain is automatic vehicle guidance (AVG) and autonomous mobile robots (AMR), in which a stereo vision system is applied on board. Results are presented with reference to a synthetic database created ad hoc to evidence some interesting cases of object/obstacle trajectories.