VisionGuard: Physics-Driven Vehicle Collision Detection and Alerting System using Deep Learning
Keywords:
Computer vision, Edge AI, Kinematic analysis, Object tracking, Vehicle collision detection, YOLO v11Abstract
Traffic-related accidents represent a major source of global mortality, often compounded by delayed emergency assistance due to manual reporting constraints. This paper introduces VisionGuard, an automated, web-based collision detection and alerting platform that integrates deep learning-based object detection, multi-object tracking, and physics-driven kinematic reasoning. Operating on live or pre-recorded traffic video streams, the system utilizes the YOLO v11 nano model to localize vehicles across four categories (cars, motorcycles, buses, and trucks) and maps them to a ByteTrack tracker to maintain unique identities across successive frames. A custom physics engine records center-point trajectories in a sliding window buffer, continuously evaluating vehicle pairs for spatial proximity (Intersection over Union and center-point Euclidean distance) and kinematic anomalies. A collision is logged when close proximity coincides with a kinetic shock (sudden velocity drop exceeding 70 %) or an abrupt angular direction change. Confirmed incidents trigger visual overlays, capture localized snapshots, and generate structured, evidence-backed PDF reports. Experimental results on real-world CCTV footage show that VisionGuard achieves a collision detection accuracy of 95.05 %, a specificity of 97.36 %, and a processing speed of 45.5 FPS under GPU acceleration, providing an explainable and reliable automated traffic monitoring layer.
References
Y. Zhang, F. Liu, S. Yue, Y. Li, and Q. Dong, “Accident detection and flow prediction for connected and automated transport systems,” Journal of Advanced Transportation, vol. 2023, no. 1, Art. no. 5041509, 2023
A. S. Bari, M. A. Falalu, M. A. Umar, Y. Y. Sulaiman, A. Gamble, and M. Baballe, “Accident detection and alerting systems: A review,” Global Journal of Research in Engineering and Computer, vol. 2, no. 1, pp. 12–24, 2022.
M. Rajamanogaran and G. Karthikeyan, “Instinctive detection of accident occurrence using numerous machine learning techniques with comparative study,” Indian Journal of Science and Technology, vol. 17, no. 17, pp. 1724–1734, Apr. 2024.
R. Bharadwaj, M. Tagad, T. Katkade, A. Ukarde, and S. Joshi, “Accident detection using deep learning,” In Proceedings of the International Conference on Intelligent Sustainable Systems, Singapore: Springer Nature Singapore, 2023, pp. 679–688.
Y. Zhang and Y. Sung, “Traffic accident detection using background subtraction and CNN encoder–transformer decoder in video frames,” Mathematics, vol. 11, no. 13, Art. no. 2884, Jun. 2023.
Y. Zhang and Y. Sung, “Traffic accident detection method using trajectory tracking and influence maps,” Mathematics, vol. 11, no. 7, Art. no. 1743, Apr. 2023.
M. A. Baballe, “Accident detection system with GPS, GSM, and buzzer,” TMP Universal Journal of Research and Review Archives, vol. 2, no. 1, pp. 28–36, Mar. 2023.
A. Ata, M. A. Khan, S. Abbas, M. S. Khan, and G. Ahmad, “Adaptive IoT empowered smart road traffic congestion control system using supervised machine learning algorithm,” The Computer Journal, vol. 64, no. 11, pp. 1672–1679, Nov. 2021.
S. B. Neelakandan, M. A. Berlin, S. Tripathi, V. B. Devi, I. Bhardwaj, and N. Arulkumar, “IoT-based traffic prediction and traffic signal control system for smart city,” Soft Computing, vol. 25, no. 18, pp. 12241–12248, Sep. 2021.
J. A. Kim, J. Y. Sung, and S. H. Park, “Comparison of Faster-RCNN, YOLO, and SSD for real-time vehicle type recognition,” In Proceedings of the IEEE International Conference on Consumer Electronics–Asia, 2020, pp. 1–4.
C. Rodrigues, S. Khan, G. Mahale, and R. D. Sardinha, “Accident detection & smart traffic system using CNN,” In Proceedings of the IEEE International Conference on Computer Vision and Machine Intelligence, 2024, pp. 1–6.
A. F. Rasheed and M. Zarkoosh, “YOLOv11 optimization for efficient resource utilization,” arXiv preprint arXiv:2412.14790, Dec. 2024.
N. Wojke, A. Bewley, and D. Paulus, “Simple online and realtime tracking with a deep association metric,” In Proceedings of the IEEE International Conference on Image Processing, 2017, pp. 3645–3649.
Y. Zhang, P. Sun, Y. Jiang, D. Yu, F. Weng, Z. Yuan, P. Luo, W. Liu, and X. Wang, “ByteTrack: Multi-object tracking by associating every detection box,” in Computer Vision – European Conference on Computer Vision (ECCV), Cham, Switzerland, 2022, pp. 1–21.
T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft COCO: Common objects in context,” in Computer Vision – European Conference on Computer Vision (ECCV), Cham, Switzerland: Springer International Publishing, 2014, pp. 740–755.
