In Situ Evaluation of Tracking Algorithms Using Time Reversed Chains

Automatic evaluation of visual tracking algorithms in the absence of ground truth is a very challenging and important problem. In the context of online appearance modeling, there is an additional ambiguity involving the correctness of the appearance model. In this paper, we propose a novel performance evaluation strategy for tracking systems based on particle filter using a time reversed Markov chain. Starting from the latest observation, the time reversed chain is propagated back till the starting time t = 0 of the tracking algorithm. The posterior density of the time reversed chain is also computed. The distance between the posterior density of the time reversed chain (at t = 0) and the prior density used to initialize the tracking algorithm forms the decision statistic for evaluation. It is postulated that when the data is generated true to the underlying models, the decision statistic takes a low value. We empirically demonstrate the performance of the algorithm against various co...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Hao Wu, Aswin C. Sankaranarayanan, Rama Chellappa
• Keywords: Computer Vision, CVPR 2007, Time Reversed Chain, Time Reversed Markov, Tracking Algorithm, Visual Tracking Algorithms, Visual Tracking Problem