Abstract
The conflict between computational overhead and detection accuracy affects nearly every Automated Accident Detection (AAD) system. Although the accuracy of detection and classification approaches has recently improved dramatically, the systems’ high computational resource requirements make them unsuitable for deployment in situations when immediate feedback is required. This paper suggests a strategy for developing an accurate, cost-efficient automatic collision identification system that can be deployed with a minimal amount of hardware. The AAD system is divided into three key phases—Detection, Tracking, and Classification and offers computationally reduced intensive algorithms for each of these stages. For the detection phase, YOLOv3, it uses a deep learning model that has been trained through knowledge distillation. Its accuracy is on par with that of YOLO (You-Only-Look-Once). On the basis of the information inference and data mining techniques COCO (Common Objects in Context) dataset, YOLOv3 surpasses all other identification techniques considering runtime complexity, averaging an astounding 30 frames/second on a low-end system. It attains an Average Precision (AP) mark of 44.8. For the tracking phase, the system makes use of SORT (Simple Online Real-time Tracking). Since a radial basis kernel with a support vector machine works efficiently, an area under the curve (or AUC) score of 0.92 is achieved. Alongside this, this paper examines a number of machine-learning techniques for the classification stage.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Road traffic injuries. World Health Organization, 21 June 2021. https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries. Accessed 20 June 2023
Caroselli, Beachler & Coleman, L.L.C., 22 September 2021. https://www.cbmclaw.com/what-percentage-of-car-accidents-are-caused-by-human-error. Accessed 01 July 2023
Kapri, P., Patane, S., Shalom, A.: Accident Detection & Alert System, IEEE (2018)
Fernandes, B., Gomes, V., Ferreira, J., Oliveira, A.: Mobile Application for Automatic Accident Detection and Multimodal Alert, IEEE (2015)
Fogue, M., Garrido, P., Martinez, F.J.: System for Automatic Notification and Severity Estimation of Automotive Accidents, IEEE (2014)
Sankpal, P.M., More, P.P.: Accident avoidance system using IR transmitter. IJRASET 5(IV) (2017)
Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464–3468 (2016). https://doi.org/10.1109/ICIP.2016.7533003
Dogru, N., Subasi, A.: Traffic accident detection using random forest classifier. In: 2018 15th Learning and Technology Conference (L&T), pp. 40–45 (2018). https://doi.org/10.1109/LT.2018.8368509
Chand, D., Gupta, S., Kavati, I.: Computer vision based accident detection for autonomous vehicles. In: 2020 IEEE 17th India Council International Conference (INDICON), pp. 1–6 (2020). https://doi.org/10.1109/INDICON49873.2020.9342226
Tsuji, T., Hattori, H., Watanabe, M., Nagaoka, N.: Development of night-vision system. IEEE Trans. Intell. Transp. Syst. 3(3), 203–209 (2002)
Wakim, C., Capperon, S., Oksman, J.: A Markovian model of pedestrian behavior. In: Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, pp. 4028–4033, October 2004
Antonini, G., Venegas, S., Thiran, J.P., Bierlaire, M.: A discrete choice pedestrian behavior model for pedestrian detection in visual tracking systems. In: Proceedings of the Advanced Concepts for Intelligent Vision Systems, Brussels, Belgium, September 2004
Shimizu, H., Poggio, T.: Direction Estimation of Pedestrian from Images, AI Memo 2003-020, Massachusetts Institute of Technology, August 2003. http://cbcl.mit.edu/cbcl/publications/aipublications/2003/AIM-2003-020.pdf
Hui, Z., Yaohua, X., Lu, M., Jiansheng, F.: Vision-based real-time traffic accident detection. In: Intelligent Control and Automation (WCICA), 2014 11th World Congress on, pp. 1035–1038, June 2014
Ren, J., Chen, Y., Xin, L., Shi, J., Li, B., Liu, Y.: Detecting and positioning of traffic incidents via video-based analysis of traffic states in a road segment. IET Intell. Transp. Syst. 10(6), 428–437 (2016)
Shafiee, M.J., Chywl, B., Li, F., Wong, A.: Fast YOLO: a fast you only look once system for real-time embedded object detection in video. J. Comput. Vis. Imaging Syst. 3 (2017). https://doi.org/10.15353/vsnl.v3i1.171
Lin, C.-J., Jeng, S.-Y., Lioa, H.-W.: A real-time vehicle counting, speed estimation, and classification system based on virtual detection Zone and YOLO. Math. Probl. Eng. 2021, 1–10 (2021). https://doi.org/10.1155/2021/1577614
Pillai, M.S., Chaudhary, G., Khari, M., et al.: Real-time image enhancement for an automatic automobile accident detection through CCTV using deep learning. Soft. Comput. 25, 11929–11940 (2021). https://doi.org/10.1007/s00500-021-05576-w
Singh, P.K., Gupta, A., Upadhyay, M., Jain, A., Khari, M., Lamba, P.S.: Multimodal driver drowsiness detection from video frames. J. Mob. Multimed. 19(02), 567–586 (2022). https://doi.org/10.13052/jmm1550-4646.19210
Behrendt, K.: Boxy vehicle detection in large images. In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 840–846 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Alam, I., Verma, A., Khari, M. (2024). Deep Learning Envisioned Accident Detection System. In: Santosh, K., et al. Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2023. Communications in Computer and Information Science, vol 2026. Springer, Cham. https://doi.org/10.1007/978-3-031-53082-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-53082-1_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53081-4
Online ISBN: 978-3-031-53082-1
eBook Packages: Computer ScienceComputer Science (R0)