Title :
A novel solution for multi-camera object tracking
Author :
Weihua Chen ; Lijun Cao ; Xiaotang Chen ; Kaiqi Huang
Author_Institution :
Center for Res. on Intell. Perception & Comput., Inst. of Autom., Beijing, China
Abstract :
The traditional multi-camera object tracking contains two steps: single camera object tracking (SCT) and inter-camera object tracking (ICT). The ICT performance strongly relies on the great results of SCT. In practice, most of current SCT methods are unperfect and products much more fragments. In this paper, a novel solution using a global tracklet association is proposed, which can provide a good ICT performance when the SCT results are not perfect. The proposed solution is also available in non-overlapping views through a new tracklet representation and experiments shows the effectiveness of the proposed novel solution in real scene.
Keywords :
cameras; image fusion; object tracking; ICT; SCT methods; global tracklet association; intercamera object tracking; multicamera object tracking; single camera object tracking; tracklet representation; Cameras; Legged locomotion; Object tracking; Target tracking; Trajectory; Uncertainty; Multi-camera object tracking; PMCSHR; global tracklet association;
Conference_Titel :
Image Processing (ICIP), 2014 IEEE International Conference on
Conference_Location :
Paris
DOI :
10.1109/ICIP.2014.7025472