Hybrid Stochastic / Deterministic Optimization for Tracking Sports Players and Pedestrians [chapter]

Robert T. Collins, Peter Carr
2014 Lecture Notes in Computer Science  
Although 'tracking-by-detection' is a popular approach when reliable object detectors are available, missed detections remain a difficult hurdle to overcome. We present a hybrid stochastic/deterministic optimization scheme that uses RJMCMC to perform stochastic search over the space of detection configurations, interleaved with deterministic computation of the optimal multi-frame data association for each proposed detection hypothesis. Since object trajectories do not need to be estimated
more » ... ly by the sampler, our approach is more efficient than traditional MCMCDA techniques. Moreover, our holistic formulation is able to generate longer, more reliable trajectories than baseline trackingby-detection approaches in challenging multi-target scenarios.
doi:10.1007/978-3-319-10605-2_20 fatcat:cgjdcuoce5a6rm3ankra2anz6u