Performance Evaluation of Random Set Based Pedestrian Tracking Algorithms
This work provides a comparative analysis of tracking algorithms for pedestrian monitoring, but it is incremental as it focuses on evaluation rather than new methods.
The paper evaluated the error performance of three random finite set based multi-object trackers for pedestrian video tracking using a dataset of 4500 frames, finding comparative results under various conditions.
The paper evaluates the error performance of three random finite set based multi-object trackers in the context of pedestrian video tracking. The evaluation is carried out using a publicly available video dataset of 4500 frames (town centre street) for which the ground truth is available. The input to all pedestrian tracking algorithms is an identical set of head and body detections, obtained using the Histogram of Oriented Gradients (HOG) detector. The tracking error is measured using the recently proposed OSPA metric for tracks, adopted as the only known mathematically rigorous metric for measuring the distance between two sets of tracks. A comparative analysis is presented under various conditions.