Dynamic subset selection for multi-camera tracking

Abstract

While multi-camera methods for object tracking tend to outperform their single-camera counterparts, the data aggregation schemes can introduce new challenges, such as resource management and algorithm complexity. We present a framework for dynamically choosing the best subset of available cameras for tracking in real-time, which reduces aggregate tracking error and resource consumption and can be applied to a variety of existing base tracking models. We demonstrate on challenging video sequences of players in a basketball game. Our method is able to successfully track targets entering and exiting camera views and through occlusions, and overcome instances of single-view tracking drift.

Wide-area Multi-camera Multi-object Tracking with Dynamic Task Decomposition

“…In order to minimize computational cost, a possible strategy is to reduce observations for evaluation, since likelihood computation is the most costly part in tracking. Some researchers propose to select a subset of cameras for tracking each target [9], while others propose to dynamically deactivate some particles [18] or cameras [15]. Another method is to distribute the computational load to multiple processors, such as the workload equalization method proposed in [19], in which camera workload is modeled as a function of the number of targets in its view.…”

Multi-camera localisation: a review

“…1 measurement correspondence (where features of an object seen from different cameras are wrapped into a common view prior to state estimation) 2 trajectory correspondence (where state estimates are computed independently in each view) (Spurlock and Souvenir, 2012;Taj and Cavallaro, 2011).…”