Object Tracking Benchmark

Object tracking has been one of the most important and active research areas in the field of computer vision. A large number of tracking algorithms have been proposed in recent years with demonstrated success. However, the set of sequences used for evaluation is often not sufficient or is sometimes biased for certain types of algorithms. Many datasets do not have common ground-truth object positions or extents, and this makes comparisons among the reported quantitative results difficult. In addition, the initial conditions or parameters of the evaluated tracking algorithms are not the same, and thus, the quantitative results reported in literature are incomparable or sometimes contradictory. To address these issues, we carry out an extensive evaluation of the state-of-the-art online object-tracking algorithms with various evaluation criteria to understand how these methods perform within the same framework. In this work, we first construct a large dataset with ground-truth object positions and extents for tracking and introduce the sequence attributes for the performance analysis. Second, we integrate most of the publicly available trackers into one code library with uniform input and output formats to facilitate large-scale performance evaluation. Third, we extensively evaluate the performance of 31 algorithms on 100 sequences with different initialization settings. By analyzing the quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.We thank the reviewers for valuable comments and suggestions. Y. Wu is supported partly by NSFC under Grants 61005027 and 61370036. J. Lim is supported partly by the ICT R&D programs of MSIP/IITP (No. 10047078 and No.14-824-09-006) and MSIP/NIPA (CITRC program No. NIPA-2014-H0401-14-1001). M.-H. Yang is supported in part by the National Science Foundation CAREER Grant 1149783 and IIS Grant 1152576. J. Lim is the corresponding author