Decoupling features via global and local contexts in multi-object tracking

Yixing Su; Hongbing Ma; Shengjin Wang

doi:10.1117/12.2653540

18 November 2022 Decoupling features via global and local contexts in multi-object tracking

Yixing Su, Hongbing Ma, Shengjin Wang

Proceedings Volume 12473, Second International Conference on Optics and Communication Technology (ICOCT 2022); 124731E (2022) https://doi.org/10.1117/12.2653540
Event: Second International Conference on Optics and Communication Technology (ICOCT 2022), 2022, Hefei, China

Abstract

Multi-object tracking (MOT) system usually consists of two tasks, object detection and re-identification (ReID). Current MOT methods tend to join detection and ReID in a single network to enhance inference speed. Such one-shot models allow joint optimization of detection and Re-ID via a shared backbone, reducing computation cost. However, the different demands of features between the two tasks in one-shot systems lead to competition in the optimization procedure. The detection task needs the features of the instances with the same class to be similar, while the ReID task needs the features of different instances to be distinguishable. Existing methods address the contradiction by disentangling the features into detection-specific and ReID-specific features. But these methods neglect the discussion of semantic interpretation of disentangling modules. In this paper, we propose a feature decoupling module, Global and Local Context-based Decoupling Module (GLCD), to disentangle features extracted by the backbone into two task-specific features. By extracting global and local contexts, the two tasks can choose different contexts by learnable parameters to enforce each self. We conduct our decoupling module into SOTA one-shot MOT method and experiments show performance improvement.

Citation Download Citation

Yixing Su, Hongbing Ma, and Shengjin Wang "Decoupling features via global and local contexts in multi-object tracking", Proc. SPIE 12473, Second International Conference on Optics and Communication Technology (ICOCT 2022), 124731E (18 November 2022); https://doi.org/10.1117/12.2653540

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Convolution

Feature extraction

Video

Network architectures

Optimization (mathematics)

Performance modeling

Sensors

Show All Keywords

Keywords/Phrases

Search In:

Publication Years