DocumentCode :
3406314
Title :
Partial motion trajectory grouping through rooted arborescence
Author :
Fan Chen ; De Vleeschouwer, C.
Author_Institution :
Sch. of Inf. Sci., Japan Adv. Insti. of Sci. & Tech., Nomi, Japan
fYear :
2012
fDate :
Sept. 30 2012-Oct. 3 2012
Firstpage :
1337
Lastpage :
1340
Abstract :
A novel method is presented for trackingmultiple deformable objects in a multiview scenario. We avoid applying fixed constraints of object sizes for object isolation, but guide the splitting/merging of objects by grouping partial motion trajectories extracted from the occupancy status of objects in the homography ground-plane. We treat this clustering task as solving a rooted arborescence problem, and investigate the performance of the proposed method by experimental results.
Keywords :
feature extraction; image motion analysis; object tracking; pattern clustering; clustering task; fixed-object size constraints; homography ground-plane; multiple deformable object tracking; multiview scenario; object isolation; object merging; object occupancy status; object splitting; partial motion trajectory grouping; rooted arborescence problem; Cameras; Feature extraction; Object tracking; Trajectory; Videos; Windows; Multi-View Tracking; Rooted Arborescence Problem; Trajectory Analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2012 19th IEEE International Conference on
Conference_Location :
Orlando, FL
ISSN :
1522-4880
Print_ISBN :
978-1-4673-2534-9
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2012.6467115
Filename :
6467115
Link To Document :
بازگشت