Abstract
Multiple-target tracking has received tremendous attention due to its wide practical applicability in video processing and analysis applications. Most existing techniques, however, suffer from the well-known "multitarget occlusion" problem and/or immense computational cost due to its use of high-dimensional joint-state representations. In this paper, we present a distributed Bayesian framework using multiple collaborative cameras for robust and efficient multiple-target tracking in crowded environments with significant and persistent occlusion. When the targets are in close proximity or present multitarget occlusions in a particular camera view, camera collaboration between different views is activated in order to handle the multitarget occlusion problem in an innovative way. Specifically, we propose to model the camera collaboration likelihood density by using epipolar geometry with sequential Monte Carlo implementation. Experimental results have been demonstrated for both synthetic and real-world video data.
Highlights
AND RELATED WORKVisual multiple-target tracking (MTT) has received tremendous attention in the video processing community due to its numerous potential applications in important tasks such as video surveillance, human activity analysis, traffic monitoring, and so forth
It can be observed that the proposed Bayesian multiplecamera tracking (BMCT) outperforms the CMCT in speed and achieves very close efficiency compared with multiple independent regular particle filters (MIPFs) and interactively distributed multiobject tracking (IDMOT)
We have proposed a Bayesian framework to solve the multitarget occlusion problem for multiple-target tracking using multiple collaborative cameras
Summary
AND RELATED WORKVisual multiple-target tracking (MTT) has received tremendous attention in the video processing community due to its numerous potential applications in important tasks such as video surveillance, human activity analysis, traffic monitoring, and so forth. MTT for targets whose appearance is distinctive is much easier since it can be solved reasonably well by using multiple independent single-target trackers. In this situation, when tracking a specific target, all the other targets can be viewed as background due to their distinct appearance. Isard and MacCormick [5] combined a multiblob likelihood function with the condensation filter and used a 3D object model providing depth ordering to solve the multitarget occlusion problem. The above solutions, which are based on a centralized process, can handle the problem of multitarget occlusion in principle, they require a tremendous computational cost due to the complexity introduced by the high dimensionality of the joint-state representation which grows exponentially in terms of the number of objects tracked.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
