Deep Learning for Visual Tracking: A Comprehensive Survey

Abstract

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 yearspredominantly 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 six key aspects of: network architecture, network exploitation, network training for visual tracking, network objective, network output, and the exploitation of correlation filter advantages. 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, and LaSOT. Finally, by conducting critical analyses of these stateof-the-art methods both 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 on 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.

Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search

“…In this section, we will give a review on greedy search based, reinforcement learning based, and ensemble learning based trackers. Due to the limited space in this paper, the following survey papers [1]- [3], [17], [18] and paper list 1 are recommended to find more related trackers.…”

Siamese Network for RGB-D Salient Object Detection and Beyond

“…A comprehensive summary of the Siamese network is beyond the scope of this work. The readers can refer to the recently released survey work [91] for more details.…”

Multi‐camera 3D ball tracking framework for sports video

“…Thus, ball tracking technique is necessary to handle the fully occlusion problem. In recent years, the visual tracking methods for generic object have been significantly developed [43]. Among them, ECO tracker is one of the most state-of-the-art trackers based on discriminative correlation filter [16].…”