Paper Info
Title
Vehicle detection and tracking using Mean Shift segmentation on semi-dense disparity maps
Abstract
This paper describes an original joint obstacle detection and tracking method based on a Mean Shift algorithm and semi-dense disparity maps. The semi-dense disparity maps are computed with a local 1D fuzzy scanline stereo matching approach. Each map is associated to a confidence map that is used to remove bad matches. The Mean Shift algorithm is applied to simultaneously extract each vehicle and track the 3D points belonging to the same vehicle along the sequence. We show that several vehicles can be efficiently detected and that a semi-dense disparity map is sufficient to reach an accurate segmentation even when occlusions occur. This paper presents some results on real image sequences acquired in the context of Advanced Driver Assistance Systems.
Year
DOI
Venue
2012
10.1109/IVS.2012.6232280
Intelligent Vehicles Symposium
Keywords
Field
DocType
computer graphics,driver information systems,fuzzy set theory,image matching,image segmentation,image sequences,object detection,object tracking,stereo image processing,1D fuzzy scanline stereo matching approach,3D point extraction,3D point tracking,advanced driver assistance system,image segmentation,image sequences,mean shift algorithm,obstacle detection,occlusions,semidense disparity map,vehicle detection,vehicle tracking
Computer vision,Object detection,Pattern recognition,Stereopsis,Computer science,Segmentation,Image segmentation,Video tracking,Artificial intelligence,Mean-shift,Real image,Scan line
Conference
ISSN
ISBN
Citations 
1931-0587
978-1-4673-2119-8
11
PageRank 
References 
Authors
0.58
16
2
Name
Order
Citations
PageRank
Sébastien Lefebvre1212.60
Sebastien Ambellouis2649.91