Static Video Compression’s Influence on Neural Network Performance

Abstract

The concept of action recognition in smart security heavily relies on deep learning and artificial intelligence to make predictions about actions of humans. To draw appropriate conclusions from these hypotheses, a large amount of information is required. The data in question are often a video feed, and there is a direct relationship between increased data volume and more-precise decision-making. We seek to determine how far a static video can be compressed before the neural network’s capacity to predict the action in the video is lost. To find this, videos are compressed by lowering the bitrate using FFMPEG. In parallel, a convolutional neural network model is trained to recognise action in the videos and is tested on the compressed videos until the neural network fails to predict the action observed in the videos. The results reveal that bitrate compression has no linear relationship with neural network performance.