Loading...

Deep Learning for Visual Tracking: A Comprehensive Survey

Marvasti Zadeh, S. M ; Sharif University of Technology | 2021

238 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/TITS.2020.3046478
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2021
  4. Abstract:
  5. Visual target tracking is one of the most sought-after yet challenging research topics in computer vision. Given the ill-posed nature of the problem and its popularity in a broad range of real-world scenarios, a number of large-scale benchmark datasets have been established, on which considerable methods have been developed and demonstrated with significant progress in recent years - predominantly by recent deep learning (DL)-based methods. This survey aims to systematically investigate the current DL-based visual tracking methods, benchmark datasets, and evaluation metrics. It also extensively evaluates and analyzes the leading visual tracking methods. First, the fundamental characteristics, primary motivations, and contributions of DL-based methods are summarized from nine key aspects of: network architecture, network exploitation, network training for visual tracking, network objective, network output, exploitation of correlation filter advantages, aerial-view tracking, long-term tracking, and online tracking. Second, popular visual tracking benchmarks and their respective properties are compared, and their evaluation metrics are summarized. Third, the state-of-the-art DL-based methods are comprehensively examined on a set of well-established benchmarks of OTB2013, OTB2015, VOT2018, LaSOT, UAV123, UAVDT, and VisDrone2019. Finally, by conducting critical analyses of these state-of-the-art trackers quantitatively and qualitatively, their pros and cons under various common scenarios are investigated. It may serve as a gentle use guide for practitioners to weigh when and under what conditions to choose which method(s). It also facilitates a discussion on ongoing issues and sheds light on promising research directions. IEEE
  6. Keywords:
  7. Antennas ; Large dataset ; Network architecture ; Surveys ; Target tracking ; Benchmark datasets ; Correlation filters ; Evaluation metrics ; Fundamental characteristics ; Ill-posed natures ; Long-term tracking ; Real-world scenario ; Visual target tracking ; Deep learning
  8. Source: IEEE Transactions on Intelligent Transportation Systems ; 2021 ; 15249050 (ISSN)
  9. URL: https://ieeexplore.ieee.org/document/9339950