Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook

TL;DR

This survey comprehensively reviews over 90 discriminative correlation filter and Siamese network-based visual object trackers, analyzing their theoretical foundations, performance across nine benchmarks, and outlining open research challenges.

Contribution

It provides a systematic review of DCF and Siamese trackers, including background theory, performance analysis, and future research directions in visual object tracking.

Findings

DCF and Siamese trackers have achieved significant progress.

Performance varies across different benchmarks and datasets.

Open challenges include robustness, speed, and generalization.

Abstract

Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image sequence, given only its initial location, and segmentation, or its rough approximation in the form of a bounding box. Discriminative Correlation Filters (DCFs) and deep Siamese Networks (SNs) have emerged as dominating tracking paradigms, which have led to significant progress. Following the rapid evolution of visual object tracking in the last decade, this survey presents a systematic and thorough review of more than 90 DCFs and Siamese trackers, based on results in nine tracking benchmarks. First, we present the background theory of both the DCF and Siamese tracking core formulations. Then, we distinguish and comprehensively review the shared as well as specific open research challenges in both these tracking paradigms. Furthermore, we thoroughly analyze the performance of DCF and Siamese trackers on nine benchmarks, covering different experimental aspects of visual tracking: datasets, evaluation metrics, performance, and speed comparisons. We finish the survey by presenting recommendations and suggestions for distinguished open challenges based on our analysis.