A Bayesian Filter for Multi-View 3D Multi-Object Tracking With Occlusion Handling
MetadataShow full item record
Funding and Sponsorship
This paper proposes an online multi-camera multi-object tracker that only requires monocular detector training, independent of the multi-camera configurations, allowing seamless extension/deletion of cameras without retraining effort. The proposed algorithm has a linear complexity in the total number of detections across the cameras, and hence scales gracefully with the number of cameras. It operates in the 3D world frame, and provides 3D trajectory estimates of the objects. The key innovation is a high fidelity yet tractable 3D occlusion model, amenable to optimal Bayesian multi-view multi-object filtering, which seamlessly integrates, into a single Bayesian recursion, the sub-tasks of track management, state estimation, clutter rejection, and occlusion/misdetection handling. The proposed algorithm is evaluated on the latest WILDTRACKS dataset, and demonstrated to work in very crowded scenes on a new dataset.
Showing items related by title, author, creator and subject.
Kim, Du Yong; Vo, Ba-Ngu; Vo, Ba Tuong; Jeon, M. (2019)This paper proposes an online multi-object tracking algorithm for image observations using a top-down Bayesian formulation that seamlessly integrates state estimation, track management, handling of false positives, false ...
Kim, Du Yong; Jeon, M. (2014)Data fusion is an important issue for object tracking in autonomous systems such as robotics and surveillance. In this paper, we present a multiple-object tracking system whose design is based on multiple Kalman filters ...
Nguyen, Nam; Bui, Hung H.; Venkatesh, Svetha; West, Geoffrey (2003)In this paper, we present a distributed surveillance system that uses multiple cheap static cameras to track multiple people in indoor environments. The system has a set of Camera Processing Modules and a Central Module ...