Enhanced video analysis framework for action detection using deep learning

Video Analytics analyzes the video content and adds brains to eyes that is analytics to camera. It extracts contents from the video by monitoring the video in real time. Normal and Abnormal human activity detection using deep learning models is a challenging task in computer vision. The detection of the same will help in detecting crime scenes which will help in preventing treacherous actions Proposed method focuses on classifying normal activities for humans in real time scenarios. The pre-processing technique for redundant frame detection, elimination and training the model efficiently using Convolutional Neural Network for classifying the activities is the main research contribution. Proposed method shows improvement in accuracy as compared to reference method which can be further implemented for on edge embedded platforms for real time applications