Learning spatio-temporal attention for multi-object tracking and re-identification in wide area motion imagery

Ruixu Liu; Theus Aspiras; Vijiyan K. Asari

doi:10.1117/12.2618503

13 June 2022 Learning spatio-temporal attention for multi-object tracking and re-identification in wide area motion imagery

Ruixu Liu, Theus Aspiras, Vijiyan K. Asari

Author Affiliations +

Proceedings Volume PC12101, Pattern Recognition and Tracking XXXIII; PC1210101 (2022) https://doi.org/10.1117/12.2618503
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

Multi-object tracking in wide-area motion imagery (WAMI) is facilitating great interest in the field of image processing that leads to numerous real-world applications. Among them, aircraft and unmanned aerial vehicles (UAV) with real-time robust visual trackers for long-term aerial maneuvering are currently attracting attention and have remarkably broadened the scope of applications of object tracking. In this paper, we present a novel attention-based feature fusion strategy, which effectively combines the template and searching region features. Our results demonstrate the efficacy of the proposed system on CLIF and UNICORN datasets.

Conference Presentation

Citation Download Citation

Ruixu Liu, Theus Aspiras, and Vijiyan K. Asari "Learning spatio-temporal attention for multi-object tracking and re-identification in wide area motion imagery", Proc. SPIE PC12101, Pattern Recognition and Tracking XXXIII, PC1210101 (13 June 2022); https://doi.org/10.1117/12.2618503

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