Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

On the detection-to-track association for online multi-object tracking

Tools
- Tools
+ Tools

Lin, Xufeng, Li, Chang-Tsun, Sanchez Silva, Victor and Maple, Carsten (2021) On the detection-to-track association for online multi-object tracking. Pattern Recognition Letters, 146 . pp. 200-207. doi:10.1016/j.patrec.2021.03.022

[img]
Preview
PDF
WRAP-On-the-detection-to-track-association-online-multi-object-tracking-2021.pdf - Accepted Version - Requires a PDF viewer.
Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0.

Download (2362Kb) | Preview
Official URL: https://doi.org/10.1016/j.patrec.2021.03.022

Request Changes to record.

Abstract

Driven by recent advances in object detection with deep neural networks, the tracking-by-detection paradigm has gained increasing prevalence in the research community of multi-object tracking (MOT).
It has long been known that appearance information plays an essential role in the detection-to-track association, which lies at the core of the tracking-by-detection paradigm. While most existing works
consider the appearance distances between the detections and the tracks, they ignore the statistical information implied by the historical appearance distance records in the tracks, which can be particularly useful when a detection has similar distances with two or more tracks. In this work, we propose a hybrid track association (HTA) algorithm that models the historical appearance distances of a track with an incremental Gaussian mixture model (IGMM) and incorporates the derived statistical information into the calculation of the detection-to-track association cost. Experimental results on three MOT benchmarks confirm that HTA effectively improves the target identification performance with a small compromise to the tracking speed. Additionally, compared to many state-of-the-art trackers, the DeepSORT tracker equipped with HTA achieves better or comparable performance in terms of the balance of tracking quality and speed.

Item Type: Journal Article
Subjects: Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Science, Engineering and Medicine > Science > Computer Science
Library of Congress Subject Headings (LCSH): Automatic tracking -- Research, Optical pattern recognition, Computer vision, Tracking radar, Signal processing -- Digital techniques, Video surveillance, Pattern recognition systems, Automated vehicles
Journal or Publication Title: Pattern Recognition Letters
Publisher: Elsevier BV
ISSN: 0167-8655
Official Date: June 2021
Dates:
DateEvent
June 2021Published
22 March 2021Available
18 March 2021Accepted
Volume: 146
Page Range: pp. 200-207
DOI: 10.1016/j.patrec.2021.03.022
Status: Peer Reviewed
Publication Status: Published
Access rights to Published version: Restricted or Subscription Access
RIOXX Funder/Project Grant:
Project/Grant IDRIOXX Funder NameFunder ID
ACC6008031Defence Science and Technology Laboratoryhttp://dx.doi.org/10.13039/100010418
EP/S035362/1PETRAS National Centre of Excellence for IoT Systems CybersecurityUNSPECIFIED
Related URLs:
  • Publisher

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us