Adam-Dingo optimized deep maxout network-based video surveillance system for stealing crime detection

Abstract

An enormous amount of video data is generated every day as a result of the widespread deployment of security cameras due to recent technological advancements. Analyzing such videos for identifying anomalies manually is an extremely challenging issue. Stealing is an issue occurring worldwide resulting in casualties and huge financial damages yearly. Efficient techniques to identify this anomaly haven’t been much researched, and hence here a novel technique is proposed. A hybrid optimized deep learning technique is proposed for detecting stealing crime from videos obtained by surveillance cameras. Firstly, the videos are summarized using Video summarization (VSUMM) method and then video is given input to the Deep Maxout Network. A deep maxout network whose weights are updated with the help of the introduced Adam-Dingo Optimizer for identifying the stealing crime event or normal event. The devised Adam-Dingo optimized Deep Maxout network is tested for its performance with metrics, such as True Positive Rate (TPR), True Negative Rate (TNR), and accuracy and is found to have attained values of 0.940, 0.936 and 0.945, respectively. Identifying stealing crime at different weather condition can be the future work. Identifying different crime events and reporting to control room can be the future work of proposed system.