Volume 8,Issue 9
Research on Unmanned‑Vehicle Safety Early‑Warning System Based on Machine Vision
The capability to deliver timely early warnings and take countermeasures during driving constitutes one of the most critical competencies for unmanned vehicles, and early‑warning solutions based on machine vision are among the most widely‑discussed ones nowadays. When travelling, unmanned vehicles need to carefully perceive their surrounding environment. This paper introduces early‑warning responses of unmanned vehicles supported by machine vision under various scenarios. Some of these early‑warning responses apply to most real‑life situations, which provides certain references for research on unmanned‑vehicle early‑warning systems.
[1] Nister D, Stewenius H, 2004, Linear Time Maximally Stable Extremal Regions. Computer Vision–ECCV 2004. Proceedings, Part II 8, 345–357.
[2] Li L, Wang Y, Zheng N, et al., 2007, Research and Development of Intelligent Analysis for Driving Behaviors. Acta Automatica Sinica, 10: 1014–1022.
[3] Wang Y, Yu R, 2024, Analysis on Influencing Factors of Vehicle Longitudinal Interaction Safety Under Human–Machine Mixed Driving. Journal of Transport Information and Safety, 42(3): 11–19.
[4] Zhou R, Wang M, Yang Z, 2016, Research on Visual Detection System Based on LabVIEW. Technology Outlook, 26(12): 166.
[5] Zhao N, Deng C, Wen Z, et al., 2025, Fast Recognition Algorithm for Salient Image Targets Based on Machine Vision. Journal of Jilin University (Engineering and Technology Edition), 55(10): 3346–3351.
[6] Zhang H, Wang K, Wang Y, 2017, Application Progress and Prospect of Deep Learning in Object Visual Detection. Acta Automatica Sinica, 43(8): 1289–1305.
[7] Tian Y, 2022, Research on Key Parallel-Vision Methods for 3D Object Detection in Traffic Scenarios. University of Science and Technology of China.
[8] Zhang H, Tian Y, Wang Y, et al., 2026, Parallel Images: From Theoretical Framework to Multimodal Intelligent-Vision Applications. Journal of Image and Graphics, 31(7): 2358–2380.
[9] Liu H, Li C, Wu Q, et al., 2023, Visual Instruction Tuning. Advances in Neural Information Processing Systems (NeurIPS).
[10] Wei J, Wang X, Schuurmans D, et al., 2022, Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. Advances in Neural Information Processing Systems (NeurIPS).
[11] Tian X, Gu J, Li B, et al., 2024, DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models. Conference on Robot Learning, PMLR.
[12] Sha H, Mu Y, Jiang Y, et al., 2023, LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving. arXiv preprint arXiv:2310.03026.
[13] Xu Z, Zhang Y, Xie E, et al., 2024, DriveGPT4: Interpretable End-to-End Autonomous Driving via Large Language Model. IEEE Robotics and Automation Letters, 9(2): 1183–1190.
[14] Li J, Zhang X, Lu Y, Gao X, Huang Y, Liu H, Wang Y, 2025, Vehicle-Road Cooperative Perception Technology and Its Development Trend for Intelligent Connected Vehicles. Acta Automatica Sinica, 51(2): 233–248.
[15] Yao D, Zhang Y, Li L, et al., 2021, Vehicle-Road Collaboration and Intelligent Technology. Journal of Transportation Systems Engineering and Information Technology, 21(5): 40–51.
