JPL Technical Report Server

Real-time detection of moving objects from moving vehicles using dense stereo and optical flow

Show simple item record Talukder, Ashit Matthies, Larry 2006-04-12T17:40:59Z 2006-04-12T17:40:59Z 2004-09-28
dc.identifier.citation IROS International Conference on Intelligent Robots and Systems, Sendai, Japan, September 28-October 2, 2004. en
dc.identifier.clearanceno 04-1405
dc.description.abstract Dynamic scene perception is very important for autonomous vehicles operating around other moving vehicles and humans. Most work on real-time object tracking from moving platforms has used sparse features or assumed flat scene structures. We have recently extended a real-time, dense stereo system to include real-time, dense optical flow, enabling more comprehensive dynamic scene analysis. We describe algorithms to robustly estimate 6-DOF robot egomotion in the presence of moving objects using dense flow and dense stereo. We then use dense stereo and egomotion estimates to identity other moving objects while the robot itself is moving. We present results showing accurate egomotion estimation and detection of moving people and vehicles under general 6-DOF motion of the robot and independently moving objects. The system runs at 18.3 Hz on a 1.4 GHz Pentium M laptop, computing 160x120 disparity maps and optical flow fields, egomotion, and moving object segmentation. We believe this is a significant step toward general unconstrained dynamic scene analysis for mobile robots, as well as for improved position estimation where GPS is unavailable. en
dc.description.sponsorship NASA/JPL en
dc.format.extent 829125 bytes
dc.format.mimetype application/pdf
dc.language.iso en_US en
dc.publisher Pasadena, CA : Jet Propulsion Laboratory, National Aeronautics and Space Administration, 2004. en
dc.subject Dynamic scene analysis en
dc.subject egomotion en
dc.subject moving object detection en
dc.subject object tracking en
dc.subject optical flow en
dc.subject visual odometry en
dc.title Real-time detection of moving objects from moving vehicles using dense stereo and optical flow en
dc.type Preprint en

Files in this item

This item appears in the following Collection(s)

Show simple item record



My Account