Paper
21 June 2024 A multi-object video tracking method based on spatial constraints
Haitao Shan, Hui Zhou, Guodong Xin, Yaowei Chang, Bing Li
Author Affiliations +
Proceedings Volume 13167, International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP 2024); 131673K (2024) https://doi.org/10.1117/12.3029770
Event: International Conference on Remote Sensing, Mapping and Image Processing (RSMIP 2024), 2024, Xiamen, China
Abstract
Aiming at technical advantages of quickly discover and real-time tracking focused on targets with UAV video, we propose a multi-object tracking method based on spatial constraints. Utilizing the pre-training model of YOLOv7, we do a little work of model modification with UAVDT dataset and a small self-made dataset, then train a special object detection model for identifying and positioning vehicles in the battlefield environment; according to features of battlefield environment, we adopt classification and grading association method to determine the correlation between detection box and object, and propose a data association method based on spatial constraints and object re-identification, compared to current popular algorithms, which effectively improved the ID_SW and reduce the number of object ID switching.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Haitao Shan, Hui Zhou, Guodong Xin, Yaowei Chang, and Bing Li "A multi-object video tracking method based on spatial constraints", Proc. SPIE 13167, International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP 2024), 131673K (21 June 2024); https://doi.org/10.1117/12.3029770
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Object detection

Target detection

Detection and tracking algorithms

Data modeling

Matrices

Video

Computer vision technology

Back to Top