Skip to the main content

Original scientific paper

https://doi.org/10.24138/jcomss-2026-0006

An Efficient Multi-Object Tracking Framework for Embedded Vision via Multi-Feature Fusion

Jianguo Zhang ; Shenzhen Institute of Artificial Intelligence and Robotics for Society
Yun Chen ; Guangdong Power Grid Co., Ltd
Wenxing Sun ; Guangdong Power Grid Co., Ltd
Yuhui Chen ; Guangdong Power Grid Co., Ltd
Junwen Yao ; Guangdong Power Grid Co., Ltd
Hua Ye ; Shenzhen Institute of Artificial Intelligence and Robotics for Society
Duanjiao Li ; Guangdong Power Grid Co., Ltd


Full text: english pdf 8.855 Kb

page 322-331

downloads: 0

cite


Abstract

Despite significant progress in single-object detec tion, existing methods still face substantial technical challenges when deployed in complex and dynamic environments. Moreover, most models lack the capability to maintain stable identity information over time, leading to limited applicability in sce narios requiring persistent tracking and reliable spatiotemporal association. These limitations become even more pronounced on resource-constrained embedded platforms, where computational efficiency and real-time performance must be carefully balanced against detection precision and robustness. To address these chal lenges, our research presents an efficient multi-object tracking framework that combines SSD-based object detection with a multi-feature fusion association strategy. The proposed method leverages complementary appearance, motion, and geometric cues to construct a unified similarity matrix, enabling robust inter-frame correspondence and reducing identity switches under challenging conditions. A Kalman-based motion model and a complete track-management scheme further enhance robustness against short-term occlusions and intermittent detection failures. The system is implemented on a resource-constrained Raspberry Pi 3B platform, with dedicated optimizations to ensure real-time performance. Extensive experiments on the VOT2017 benchmark demonstrate that the proposed approach achieves a favorable balance between accuracy, stability, and computational efficiency. These results highlight the practicality of deploying the frame work in real-world embedded vision applications and provide a strong foundation for future extensions incorporating learned temporal models and lightweight re-identification modules.

Keywords

Multi-object tracking; Object detection; Similarity-based association; Real-time tracking

Hrčak ID:

353720

URI

https://hrcak.srce.hr/353720

Publication date:

20.11.2026.

Visits: 0 *