Detection of Video Anomaly in Public With Deep Learning Algorithm

Abstract

For traffic control and public safety, predicting the movement of people is crucial. The presented scheme entails the development of a wider network that can better satisfy created synthetic images by connecting spatial representations to temporal ones. The authors exclusively use the frames from those occurrences to create the dense optical flow for their corresponding normal events. In order to eliminate false-positive detection findings, they determine the local pixel reconstruction error. This particle prediction model and a likelihood model for giving these particles weights are both suggested. These models effectively use the variable-sized cell structure to produce sceneries with variable-sized sub-regions. It also successfully extracts and utilizes the video frame's size, motion, and position information. On the UCSD and LIVE datasets, the proposed framework is evaluated with the most recent algorithms reported in the literature. With a significantly shorter processing time, the suggested technique surpasses state-of-the-art techniques in relation to decreased equal error rate .