Real time action recognition from video footage

Abstract

Crime rate is increasing proportionally with the increasing rate of the population. The most prominent approach was to introduce Closed-Circuit Television (CCTV) camera-based surveillance to tackle the issue. Video surveillance cameras have added a new dimension to detect crime. Several research works on autonomous security camera surveillance are currently ongoing, where the fundamental goal is to discover violent activity from video feeds. From the technical viewpoint, this is a challenging problem because analyzing a set of frames, i.e., videos in temporal dimension to detect violence might need careful machine learning model training to reduce false results. This research focused on this problem by integrating state-of-the-art Deep Learning methods to ensure a robust pipeline for autonomous surveillance for detecting violent activities, e.g., kicking, punching, and slapping. Initially, we designed a dataset of this specific interest, which were 600 videos (200 for each action). Later, we have utilized existing pre-trained model architectures to extract features, followed by classification and accuracy analysis.Also, We have classified our models’ accuracy, confusion matrix on different pre-trained architectures like VGG16, InceptionV3, ResNet50 and MobileNet V2. Among the pre-trained models VGG16 and MobileNet V2 performed better.