A Survey of Appearance Models in Visual Object Tracking

TL;DR

This survey comprehensively reviews 2D appearance models used in visual object tracking, categorizing them by feature construction and statistical modeling, and discusses recent advances, challenges, and benchmark resources.

Contribution

It provides a detailed, module-based review of 2D appearance models, including their construction, categorization, and evaluation resources, aiding understanding of recent developments.

Findings

Categorized appearance models by feature and model mechanisms

Analyzed models from theoretical and practical perspectives

Reviewed benchmark datasets and source codes

Abstract

Visual object tracking is a significant computer vision task which can be applied to many domains such as visual surveillance, human computer interaction, and video compression. In the literature, researchers have proposed a variety of 2D appearance models. To help readers swiftly learn the recent advances in 2D appearance models for visual object tracking, we contribute this survey, which provides a detailed review of the existing 2D appearance models. In particular, this survey takes a module-based architecture that enables readers to easily grasp the key points of visual object tracking. In this survey, we first decompose the problem of appearance modeling into two different processing stages: visual representation and statistical modeling. Then, different 2D appearance models are categorized and discussed with respect to their composition modules. Finally, we address several issues of interest as well as the remaining challenges for future research on this topic. The contributions of this survey are four-fold. First, we review the literature of visual representations according to their feature-construction mechanisms (i.e., local and global). Second, the existing statistical modeling schemes for tracking-by-detection are reviewed according to their model-construction mechanisms: generative, discriminative, and hybrid generative-discriminative. Third, each type of visual representations or statistical modeling techniques is analyzed and discussed from a theoretical or practical viewpoint. Fourth, the existing benchmark resources (e.g., source code and video datasets) are examined in this survey.