Tracking multiple targets with visual sensors is a challenging problem, especially when efficiency is an issue. Occlusions, if not properly handled, are a major source of failure. Solutions supporting principled occlusion reasoning have been proposed but are yet unpractical for online applications. This article presents a new solution which effectively manages the trade-off between reliable modeling and computational efficiency. The Hybrid Joint-Separable (HJS) filter is derived from a joint Bayesian formulation of the problem, and shown to be efficient while optimal in terms of efficient belief representation. Computational efficiency is achieved by employing a forward MRF approximation to joint dynamics and an incremental algorithm for posterior update with an appearance likelihood that implements a physically-based model of the occlusion process. Its real time MonteCarlo implementation achieves accurate tracking during partial occlusions, while in case of complete occlusion tracking hypotheses are bound to estimated occlusion volumes. Experiments show that the proposed algorithm is very robust and able to resolve even long term complete occlusions between targets with identical appearance
A Joint-Separable Filter for Multitarget Tracking
Lanz, Oswald
2005-01-01
Abstract
Tracking multiple targets with visual sensors is a challenging problem, especially when efficiency is an issue. Occlusions, if not properly handled, are a major source of failure. Solutions supporting principled occlusion reasoning have been proposed but are yet unpractical for online applications. This article presents a new solution which effectively manages the trade-off between reliable modeling and computational efficiency. The Hybrid Joint-Separable (HJS) filter is derived from a joint Bayesian formulation of the problem, and shown to be efficient while optimal in terms of efficient belief representation. Computational efficiency is achieved by employing a forward MRF approximation to joint dynamics and an incremental algorithm for posterior update with an appearance likelihood that implements a physically-based model of the occlusion process. Its real time MonteCarlo implementation achieves accurate tracking during partial occlusions, while in case of complete occlusion tracking hypotheses are bound to estimated occlusion volumes. Experiments show that the proposed algorithm is very robust and able to resolve even long term complete occlusions between targets with identical appearanceI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
