Research Article
Accident Detection System Using Video Data
@INPROCEEDINGS{10.1007/978-3-031-66044-3_24, author={Rahul Vanukuri and Rohith Anagula and Ganesh Poladasari and Swathi Kothapalli}, title={Accident Detection System Using Video Data}, proceedings={Pervasive Knowledge and Collective Intelligence on Web and Social Media. Second EAI International Conference, PerSOM 2023, Hyderabad, India, November 24--25, 2023, Proceedings}, proceedings_a={PERSOM}, year={2024}, month={8}, keywords={CNN Accidental zones Geotagging Reverse coding}, doi={10.1007/978-3-031-66044-3_24} }- Rahul Vanukuri
Rohith Anagula
Ganesh Poladasari
Swathi Kothapalli
Year: 2024
Accident Detection System Using Video Data
PERSOM
Springer
DOI: 10.1007/978-3-031-66044-3_24
Abstract
In this research, we suggested an accident detection system that enables the camera while driving and detects accidents and alerts the nearest area emergency contacts. The accident detection is handled by using CNN (convolution neural networks) and the location details are handled by Google geocoding and reverse coding. The details of the location and occurrence of the accident details are stored in the app database. The video is also a collection of frames and hence we can also detect multiple accidents in different frames and can also predict the likeliness of the accident occurrence by probability. The live featuring of videos also help to detect different accidental zones around the state or country. The system certainly gives a lot of chances to balance the human loss ratio in accidents and gain safe roads among the different places. The data analysis can also be done to ensure the accidental warning signs can be posted among the most important spots after the analysis in different locations.
