GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 43; no. 5; pp. 1562 - 1577
• Main Authors: Huang, Lianghua, Zhao, Xin, Huang, Kaiqi
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Annotations; benchmark dataset; Benchmark testing; Object motion; Object tracking; Occlusion; performance evaluation; Protocols; Servers; Tracking; Training; Video data
• ISSN: 0162-8828; 1939-3539; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2019.2957464

We introduce here a large tracking database that offers an unprecedentedly wide coverage of common moving objects in the wild, called GOT-10k. Specifically, GOT-10k is built upon the backbone of WordNet structure <xref ref-type="bibr" rid="ref1">[1] and it populates the majority of over 560 classes of moving objects and 87 motion patterns, magnitudes wider than the most recent similar-scale counterparts <xref ref-type="bibr" rid="ref19">[19] , <xref ref-type="bibr" rid="ref20">[20] , <xref ref-type="bibr" rid="ref23">[23] , <xref ref-type="bibr" rid="ref26">[26] . By releasing the large high-diversity database, we aim to provide a unified training and evaluation platform for the development of class-agnostic, generic purposed short-term trackers. The features of GOT-10k and the contributions of this article are summarized in the following. (1) GOT-10k offers over 10,000 video segments with more than 1.5 million manually labeled bounding boxes, enabling unified training and stable evaluation of deep trackers. (2) GOT-10k is by far the first video trajectory dataset that uses the semantic hierarchy of WordNet to guide class population, which ensures a comprehensive and relatively unbiased coverage of diverse moving objects. (3) For the first time, GOT-10k introduces the one-shot protocol for tracker evaluation, where the training and test classes are zero-overlapped . The protocol avoids biased evaluation results towards familiar objects and it promotes generalization in tracker development. (4) GOT-10k offers additional labels such as motion classes and object visible ratios, facilitating the development of motion-aware and occlusion-aware trackers. (5) We conduct extensive tracking experiments with 39 typical tracking algorithms and their variants on GOT-10k and analyze their results in this paper. (6) Finally, we develop a comprehensive platform for the tracking community that offers full-featured evaluation toolkits, an online evaluation server, and a responsive leaderboard. The annotations of GOT-10k's test data are kept private to avoid tuning parameters on it.