Submit your paper : editorIJETjournal@gmail.com

Paper Title : ACCIDENT DETECTION USING DEEP LEARNING UNDER BAD CC TV MONITORING CONDITIONS

ISSN : 2395-1303
Year of Publication : 2022
10.5281/zenodo.7221341

Authors: Dr Subba Reddy Borra, Putchakayala Varsha Saisri, Ramini Arthi, Thallada Harika

         


Abstract
This project will introduce and apply the Object Detection and Tracking System (ODTS) along with the well-known Faster Regional Convolution Neural Network (Faster R-CNN) for Object Detection and Conventional Object Tracking algorithm for automatic detection and monitoring of unexpected events on CCTVs in tunnels, which are likely to include (1) Wrong-Way Driving (WWD), (2) Stop, (3) Person out of vehicle in tunnel, and (4) Fire. To acquire Bounding Box (Bbox) results by Object Detection, ODTS accepts a video frame in time as an input. It then compares the Bboxes of the current and previous video frames to assign a unique ID number to each moving and identified object. This technique makes it feasible to follow a moving item in real time, something that is typically not achievable with other object detection frameworks. A dataset of event photos in tunnels was used to train a deep learning model in ODTS, which resulted in Average Precision (AP) values for the target objects Car, Person, and Fire of 0.8479, 0.7161, and 0.9085, respectively. The Tunnel CCTV Accident Detection System was then tested using four accident videos that included each accident, based on a trained deep learning model. As a result, the system has a 10-second detection time for all accidents. The more crucial point is that, as the training dataset grows in size, the detection ability of ODTS could be automatically improved without any changes to the programme codes.

Reference
[1] E. S. Lee, W. Choi, D. Kum, “Bird’s eye view localization of surrounding vehicles :Longitudinal and lateral distance estimation with partial appearance,” Robotics and Autonomous Systems, 2019, vol. 112, pp. 178-189. [2] L. Cao, Q. Jiang, M. Cheng, C. Wang, “Robust vehicle detection by combining deep features with exemplar classification,” Neurocomputing, 2016, vol. 215, pp. 225-231. [3] A. Arinaldi, J. A. Pradana, A. A. Gurusinga, “Detection and classification of vehicles for traffic video analytics,” Procedia computer science, 2018, vol. 144, pp. 259-268. [4] K. B. Lee, H. S. Shin, D. G. Kim, “Development of a deep-learning based automatic tunnel incident detection system on cctvs,” in Proc. Fourth International Symposium on Computational Geomechanics, 2018, pp. 140-141. [5] S. Ren, K. He, R. Girshick, J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” in Proc. Neural Information Processing Systems, 2015, pp. 91-99. [6] A. Bewley, Z. Zongyuan, L. Ott, F. Ramos, B. Upcroft, “Simple Online and Realtime Tracking,” in Proc. IEEE International Conference on Image Processing, 2016, pp. 3464-3468. [7] K. B. Lee, H. S. Shin, D. G. Kim, “Development of a deep-learning based automatic tracking of moving vehicles and incident detection processes on tunnels,” Korean Tunnelling and Underground Space Association, 2018, vol. 20, no.6, pp. 1161-1175. [8] C. Dicle, M. Sznaier, and O. Camps, “The way they move: Tracking multiple targets with similar appearance,” in International Conference on Computer Vision, 2013. [9] S. H. Rezatofighi, A. Milan, Z. Zhang, A. Dick, Q. Shi, and I. Reid, “Joint Probabilistic Data Association Revisited,” in International Conference on Computer Vision, 2015. [10] C. Kim, F. Li, A. Ciptadi, and J. M. Rehg, “Multiple Hypothesis Tracking Revisited,” in International Conference on Computer Vision, 2015.
Keywords
— ACCIDENT DETECTION USING DEEP LEARNING UNDER BAD CC TV MONITORING CONDITIONS