Beyond Traditional Single Object Tracking: A Survey

TL;DR

This survey reviews recent advances in single object tracking, highlighting novel techniques like sequence models and reinforcement learning, and provides a comparative analysis of their performance on benchmarks.

Contribution

It introduces a new categorization of tracking methods based on emerging techniques and trends, and offers insights and future directions for research in the field.

Findings

Comparative performance analysis on popular benchmarks.

Identification of pros and cons of various approaches.

Guidance for non-traditional techniques in tracking.

Abstract

Single object tracking is a vital task of many applications in critical fields. However, it is still considered one of the most challenging vision tasks. In recent years, computer vision, especially object tracking, witnessed the introduction or adoption of many novel techniques, setting new fronts for performance. In this survey, we visit some of the cutting-edge techniques in vision, such as Sequence Models, Generative Models, Self-supervised Learning, Unsupervised Learning, Reinforcement Learning, Meta-Learning, Continual Learning, and Domain Adaptation, focusing on their application in single object tracking. We propose a novel categorization of single object tracking methods based on novel techniques and trends. Also, we conduct a comparative analysis of the performance reported by the methods presented on popular tracking benchmarks. Moreover, we analyze the pros and cons of the presented approaches and present a guide for non-traditional techniques in single object tracking. Finally, we suggest potential avenues for future research in single-object tracking.