MOT16: A Benchmark for Multi-Object Tracking

TL;DR

The paper introduces MOT16, a comprehensive benchmark dataset for evaluating multi-object tracking algorithms, with detailed annotations and multiple object classes to facilitate standardized performance assessment.

Contribution

It provides an updated, extensively annotated benchmark dataset for multi-object tracking, including multiple object classes and visibility levels, enhancing evaluation consistency.

Findings

Increased number of labeled objects in MOT16 compared to previous datasets.

Annotations include multiple object classes and visibility levels.

Benchmark facilitates standardized evaluation of multi-object tracking methods.

Abstract

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 reseach. Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking methods. The first release of the benchmark focuses on multiple people tracking, since pedestrians are by far the most studied object in the tracking community. This paper accompanies a new release of the MOTChallenge benchmark. Unlike the initial release, all videos of MOT16 have been carefully annotated following a consistent protocol. Moreover, it not only offers a significant increase in the number of labeled boxes, but also provides multiple object classes beside pedestrians and the level of visibility for every single object of interest.