A survey of video human behaviour recognition Methodologies in the Perspective of Spatial-Temporal

Currently, video human behaviour recognition is the most foundational task of computer vision. The conventional recognition frameworks are building based on the images only, with current the wide usage of surveillance video as well as human behaviours are increasingly related to temporal information, video-based behaviour recognition has been widely studied by current researchers. This paper addresses multiple current research works and does the comparison between the variants of these algorithms. The methodologies are considered to be separated into traditional recognition and deep learning based methods which have reached the highest accuracy during current research works. Our paper does the comparison of existing frameworks and datasets which are related to video-type datasets only. We investigated multiple types of neural networks which are utilized for behaviour information extraction, as well as the challenges facing for our conventional and current methods. The deep learning based methodology for extracting both spatialtemporal information has involved plenty of frameworks. We compared the pros and cons of current existing works and provide the further research directions based on existing works