Thakare, Kamalakar Vijay Dogra, Debi Prosad Choi, Heeseung Kim, Haksub KIM, IG JAE 2024-01-19T11:01:12Z 2024-01-19T11:01:12Z 2022-05-24 2022-11 1524-9050 https://pubs.kist.re.kr/handle/201004/114444 Detection and localization of road accidents in real-time is an integral part of the Intelligent Transportation System (ITS). Even though the existing road accident detection methods show promising results, the process suffers from some drawbacks. For example, existing methods require a large number of sample videos for feature learning. Moreover, features such as temporal gradients or flow fields are time-consuming. To address these issues, we introduce a new method that uses objects and their positions to detect accidents in real-time. Apart from localization of the accident events in videos, we perform a high-level post processing to describe the severity and context of an accident. Firstly, we divide an input video into pre-accident, accident and post-accident stages to extract object interactions. These interaction proposals are then filtered using a refinement algorithm. We then adopt an iterative training procedure to classify normal and accident interactions. We also highlight the damaged zone using heat maps. Finally, we generate high-level textual descriptions to quantify the context and severity of an accident. We have trained the proposed model using offline setups. However, it can be deployed online to detect road accident events in real-time by taking the video inputs directly from the CCTV camera. Moreover, with a minimal supervision, the model can be retrained for online surveillance. Extensive experiments carried out on UCF Crime and CADP datasets reveal that the proposed framework achieves state-of-the-art performance when compared with the recently proposed accident event detection methods in terms of AUC (UCF Crime: 69.70% and CADP: 72.59%) and FAR (UCF Crime: 0.8 and CADP: 2.2). The high-level description of the accident is an added advantage that will certainly help the traffic police to react in a timely manner. English Institute of Electrical and Electronics Engineers Object Interaction-Based Localization and Description of Road Accident Events Using Deep Learning Article 10.1109/TITS.2022.3170648 1 IEEE Transactions on Intelligent Transportation Systems, v.23, no.11, pp.20601 - 20613 IEEE Transactions on Intelligent Transportation Systems 23 11 20601 20613 N scie scopus 000791733600001 Engineering, Civil Engineering, Electrical & Electronic Transportation Science & Technology Engineering Transportation Article; Early Access Proposals Feature extraction Road accidents Videos Roads Location awareness Task analysis Anomaly detection road accident detection moving object interactions object localization