To address the issues of large blind spots and safety hazards during aircraft towing operations,a collision avoidance detection method integrating depth cameras and convolutional neural network(CNN) models was proposed. The CNN model was employed to automatically identify environmental targets,while the depth camera captured target distance information. The combined use of both enabled precise obstacle localization during the towing process. The trained CNN model and ZED2i binocular camera were deployed on the aircraft tractor,with communication facilitated via a CAN bus. Obstacle avoidance experiments were conducted in a test field. The results demonstrate that the constructed CNN model achieves a recognition accuracy of 0.911 and a recall rate of 0.803.Within a 10-meter ranging range,the distance measurement error remains below 0.3 meters,providing technical reference for collision avoidance safety detection during aircraft tractor towing operations.
SUN Feng-yuan, ZHANG Jun, HUANG Ming-hui, XIANG Fu-yao, WANG Yi-xuan, LIU Yu-xin.
Design of Aircraft Tractor Anti-collision Safety Detection System Based on Convolutional Network and Depth Camera[J].
Science Technology and Engineering, 2026, 26(4): 1728-1734 DOI:10.12404/j.issn.1671-1815.2500161
ZhangJun, WenChuan, YangXing, et al. Design of electric drive aircraft tractor control system based on ADRC[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(5): 1017-1026.
ZhangJun, HuangMinghui, WangYuelin, et al. Research on trajectory tracking of aircraft tractor based on MPC[J]. Journal of Beijing University of Aeronautics and Astronautics, 2025, 51(9): 2916-2926.
TangWei, ZhongPei, YuanBinbin, et al. Design and application of active collision avoidance warning and driver fatigue detection system for tractors[J]. Aviation Maintenance & Engineering, 2022(2): 32-33.
ZhangYue, WangJing, WangDingheng, et al. Dynamic obstacle avoidance method for unmanned vehicles based on pedestrian trajectory prediction[J]. Systems Engineering and Electronic Technology, 2025, 47(7): 2371-2382.
LiLifan, CaoPengbin, DuBing, et al. Pedestrian detection method based on LiDAR and depth camera fusion[J]. Laser & Infrared, 2024, 54(10): 1547-1553.
[11]
ZhuZ, WuF, SunW, et al. Depth estimation based on mmwave radar and camera fusion with attention mechanisms and multi-scale features for autonomous driving vehicles[J]. Electronics. 2025, 14(2): 300.
FanYalong, LiQi, YuLingjun. Safety clothing monitoring system for smelting workers based on deep learning[J]. Science Technology and Engineering, 2023, 23(31): 13626-13631.
[14]
JiangY, LuK, YangZ, et al. Monocularvisual anti-collision method based on residual mixed attention for storage and retrieval machines[J]. Expert Systems with Applications, 2024, 255: 124640.
YangMing, HanXu, JinYuanyuan, et al. Automatic ship-bridge collision prevention control system based on machine vision technology[J]. Ship Science and Technology. 2023, 45(5): 144-147.
[19]
TaromiA D, KlidbaryS H. A novel data-driven algorithm for object detection, tracking, distance estimation, and size measurement in stereo vision systems[J]. Multimedia Tools and Applications, 2024, 21(7): 993-1004.
ZhaoXiaolin, ZhangQirui, DongJiacheng, et al. Cooperative collision avoidance method for multiple UAVs based on vision sharing[J]. Fire Control & Command Control, 2023, 48(10): 65-72, 83.
SongJingjing, ZhangZhenli. Small target traffic sign detection algorithm based on YOLOv8n[J]. Science Technology and Engineering, 2024, 24(36): 15548-15557.
XuHuizhi, JiangShisen, WangXiuqing, et al. Vehicle target detection and ranging based on deep learning for in-vehicle images[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(1): 185-197.