Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
This provides a standardized framework for researchers in computer vision to evaluate and improve multiple object tracking methods, though it is incremental as it builds on existing benchmarking efforts.
The authors introduced a benchmark for Multiple Object Tracking to standardize evaluation, analyzing nearly 50 state-of-the-art trackers on over 11,000 frames to identify trends and weaknesses in the field.
Standardized benchmarks are crucial for the majority of computer vision applications. Although leaderboards and ranking tables should not be over-claimed, benchmarks often provide the most objective measure of performance and are therefore important guides for research. We present a benchmark for Multiple Object Tracking launched in the late 2014, with the goal of creating a framework for the standardized evaluation of multiple object tracking methods. This paper collects the two releases of the benchmark made so far, and provides an in-depth analysis of almost 50 state-of-the-art trackers that were tested on over 11000 frames. We show the current trends and weaknesses of multiple people tracking methods, and provide pointers of what researchers should be focusing on to push the field forward.