Deep Learning for Visual Tracking: A Comprehensive Survey

By Seyed Mojtaba Marvasti-Zadeh, Li Cheng, Hossein Ghanei-Yakhdan, Shohreh Kasaei. IEEE transactions on intelligent transportation systems (Print), 2019

361 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1fbb4201af091aef55360f113ba35814063923e4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Huchuan Lu
2. Chao Ma
3. Junsong Yuan
4. Dong Wang

In Computer Vision and Pattern Recognition

1. Huchuan Lu
2. Dong Wang
3. Junsong Yuan
4. Ming-Hsuan Yang
5. Chao Ma
6. Luc Van Gool
7. G. Wang
8. Chunluan Zhou

Citations in the corpus

• Learning Distilled Collaboration Graph for Multi-Agent Perception (2021, neutral): “, 2D/3D object detection [18, 27], tracking [23, 22] and segmentation [25, 16], etc.”
• AiATrack: Attention in Attention for Transformer Visual Tracking (2022, background): “It has gained increasing attention because of its wide range of applications [40,18].”
• Transformer Tracking (2021, background): “Many efforts have been done in recent years [23, 28], however, designing a high-accuracy and real-time tracker is still a challenging task.”