Context-aware model training for attention-based multicamera multiobject tracking

Miguel M. Ortiz; Francisco J. Iriarte; Hugo D. Rodríguez; Luis Unzueta; Luis M. Bergasa

doi:10.1117/12.3034014

13 November 2024 Context-aware model training for attention-based multicamera multiobject tracking

Miguel M. Ortiz, Francisco J. Iriarte, Hugo D. Rodríguez, Luis Unzueta, Luis M. Bergasa

Author Affiliations +

Proceedings Volume 13206, Artificial Intelligence for Security and Defence Applications II; 132060K (2024) https://doi.org/10.1117/12.3034014
Event: Security + Defence, 2024, Edinburgh, United Kingdom

Abstract

Attention-based Siamese networks have shown remarkable results for occlusion-aware single-camera Multi-Object Tracking (MOT) applied to persons as they can effectively combine motion and appearance features. However, expanding their usage for multi-camera MOT in crowded areas such as train stations and airports is challenging. In these kinds of scenarios, there is a higher visual appearance variability of people as the viewpoints from where they are observed while they move could be very diverse. This adds extra difficulty to the already high variability coming from partial occlusions and body pose differences (standing, sitting, or lying). Besides, attention-based MOT methods are computationally intensive and therefore difficult to scale to multiple cameras. To overcome these problems, in this paper, we propose a method that exploits contextual information of the scenario such as the viewpoint, occlusion, and pose-related visual appearance characteristics of persons to improve the inter and intra feature representations in attention-based Siamese networks. Our approach combines a smart context-aware training data batching and hard triplet mining strategy with an automated model complexity tuning procedure to train the optimal model for the scenario. This method improves the fusion of motion and appearance features of persons for the data association cost matrix of the MOT algorithm. Experimental results, validated on the MOT17 dataset, demonstrate the effectiveness and efficiency of our approach, showcasing promising results for real-world applications requiring robust MOT capabilities in multi-camera setups.

Conference Presentation

Citation Download Citation

Miguel M. Ortiz, Francisco J. Iriarte, Hugo D. Rodríguez, Luis Unzueta, and Luis M. Bergasa "Context-aware model training for attention-based multicamera multiobject tracking", Proc. SPIE 13206, Artificial Intelligence for Security and Defence Applications II, 132060K (13 November 2024); https://doi.org/10.1117/12.3034014

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