Cited by 705Video Surveillance and Tracking MethodsAdvanced Image and Video Retrieval TechniquesVisual Attention and Saliency Detection

A survey of appearance models in visual object tracking

Open access
Li, Xi, Hu, Weiming, Shen, Chunhua, Zhang, Zhongfei, Dick, Anthony, Hengel, Anton Van Den·2013·ACM Transactions on Intelligent Systems and Technology

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. Despite extensive research on this topic, it still suffers from difficulties in handling complex object appearance changes caused by factors such as illumination variation, partial occlusion, shape deformation, and camera motion. Therefore, effective modeling of the 2D appearance of tracked objects is a key issue for the success of a visual tracker. 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 fourfold. 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 codes and video datasets) are examined in this survey.

Integrity signals

Registry

Crossref · 10.1145/2508037.2508039

Cites

212 of 212 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Cites

Flagged first, then by citations

2 of the 214 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Authors
Li, X., Hu, W., Shen, C., Zhang, Z., Dick, A., & Hengel, A. V. D.
Affiliations
  • Chinese Academy of Sciences (CN)
  • The University of Adelaide (AU)
  • Binghamton University (US)
Venue
ACM Transactions on Intelligent Systems and Technology
Published
2013-09
Volume
4
Issue
4
Pages
1-48
ISSN
  • 2157-6904 (ISSN-L)
  • 2157-6912
OpenAlex
W1984914017
Cited by
705
References
214
Citations by year
2026: 4 · 2025: 7 · 2024: 15 · 2023: 26 · 2022: 30 · 2021: 50 · 2020: 51 · 2019: 81 · 2018: 98 · 2017: 97 · 2016: 111 · 2015: 83 · 2014: 47 · 2013: 5
FWCI
92.20
Type
journal article
Language
en
Open access
Locations
  • ACM Transactions on Intelligent Systems and Technology (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Adelaide Research & Scholarship (AR&S) (University of Adelaide) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Australian Research Council
  • National Natural Science Foundation of China (60935002)
  • Ministry of Science and Technology of the People's Republic of China (2012AA012504, 2012CB316400)
  • Natural Science Foundation of Beijing Municipality (4121003)
  • Division of Information and Intelligent Systems (IIS-0812114, CCF-1017828)
  • Division of Computing and Communication Foundations (IIS-0812114, CCF-1017828)
  • Guangdong Natural Science Foundation (S2012020011081)
  • Zhejiang Provincial Engineering Center onMedia Data Cloud Processing and Analysis
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
visual object tracking, visual representation, statistical modeling, tracking-by-detection, generative models, discriminative models, hybrid generative-discriminative models, illumination variation, partial occlusion, shape deformation, camera movement

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review