Tehnički vjesnik, Vol. 33 No. 5, 2026.
Izvorni znanstveni članak
https://doi.org/10.17559/TV-20251101003108
A Collaborative YOLOv5-GA-Net Framework for Real-Time Stereo 3D Object Detection in Autonomous Driving
Chunsheng Li
; School of Intelligent Science and Technology, Geely University of China, No. 123, Section 2, Chengjian Avenue, Eastern New District, ChengDu, 641423, China
*
Bing Liu
; School of UAV Industry, Chengdu Aeronautic Polytechnic University, No. 699 East 7th Road, Checheng, Longquanyi District, Chengdu 610100, Sichuan, China
Run Wang
; School of Intelligent Science and Technology, Geely University of China, No. 123, Section 2, Chengjian Avenue, Eastern New District, ChengDu, 641423, China
Jianlin Chen
; School of Intelligent Science and Technology, Geely University of China, No. 123, Section 2, Chengjian Avenue, Eastern New District, ChengDu, 641423, China
* Dopisni autor.
Sažetak
Accurate and real-time 3D perception is essential for autonomous driving, particularly under occlusion, low illumination, and adverse weather conditions. To enhance the robustness and efficiency of stereo-based 3D detection, this study proposes YGS-Net, a dual-branch collaborative framework that integrates an improved YOLOv5 detector with a guided aggregation stereo-matching network. The detection branch incorporates coordinate attention, a bidirectional feature pyramid, and a DIoU regression loss to strengthen multi-scale feature representation and box localization. The depth branch produces dense and reliable disparity maps through GA-Net. A collaborative fusion mechanism maps each 2D detection to its corresponding disparity region and estimates depth via region-averaged disparity. Experiments on the KITTI dataset demonstrate that YGS-Net achieves 75.13% AP_3D (moderate) for the "car" category, outperforming PL++, DSGN, LIGA-Stereo, and YOLOStereo3D. Real-world tests show a relative ranging error below 2.5% within 20 meters and real-time performance at ~ 42 FPS. The results indicate that YGS-Net provides a balanced and reliable purely visual 3D perception solution for complex traffic environments.
Ključne riječi
autonomous driving; binocular vision; collaborative fusion; object detection; YOLOv5
Hrčak ID:
350437
URI
Datum izdavanja:
31.8.2026.
Posjeta: 0 *