Information-Maximizing Sampling to Promote Tracking-by-Detection
This addresses the problem of improving robustness in visual tracking for applications like surveillance and robotics, though it appears incremental as it builds on existing tracking-by-detection methods.
The paper tackled the problem of sample selection in tracking-by-detection algorithms by introducing most informative sampling, which selects samples that challenge the classifier, and proposed an active discriminative co-tracker with an adversarial sampler. The result is that the proposed tracker outperforms state-of-the-art trackers on various benchmark videos.
The performance of an adaptive tracking-by-detection algorithm not only depends on the classification and updating processes but also on the sampling. Typically, such trackers select their samples from the vicinity of the last predicted object location, or from its expected location using a pre-defined motion model, which does not exploit the contents of the samples nor the information provided by the classifier. We introduced the idea of most informative sampling, in which the sampler attempts to select samples that trouble the classifier of a discriminative tracker. We then proposed an active discriminative co-tracker that embed an adversarial sampler to increase its robustness against various tracking challenges. Experiments show that our proposed tracker outperforms state-of-the-art trackers on various benchmark videos.