ACCIDENT DETECTION WITH CCTV USING CONVOLUTIONAL
Keywords:
Convolutional Neural Network; Accident Detection; Deep Learning; Video Classification; Recurrent Neural NetworkAbstract
Accidents have been a major cause of deaths in India. From past decade
surveillance cameras have been installed for security purposes on several roads and are still
being installed, but those surveillance cameras aren’t being used to their fullest. Also, there
isn’t enough of man power to survey each and every road, each and every surveillance video.
More than 80% of accident-related deaths occur not due to the accident itself but the lack of
timely help reaching the accident victims. The intent is to create a system which would detect
an accident based on the live feed of video from a CCTV camera installed on a road. The
idea is to take each frame of a video and run it through a deep learning convolution neural
network model which has been trained to classify frames of a video into accident or nonaccident.
Convolutional Neural Networks has proven to be a fast and accurate approach to
classify images.
