A Study on Handcrafted Features Based Models in Human Actions Recognitions | Original Article

ABSTRACT:

The vision-based comprehension in video sequences entices several real-life applications such as gaming, robots, patients monitoring, content-based retrieval, video surveillance, and security. One of the ultimate ambitions of artificial intelligence society is to produce an autonomous system that can be identified and interpret human behavior and activities in video sequences properly. Over the decade, numerous efforts are made to detect the human activity in films but nevertheless, it is a tough work owing to intra-class action similarities, occlusions, view variations and ambient factors. These methods are divided into handwritten features based descriptors and automatically learned feature based on deep architectures. The suggested action recognition framework is separated into handmade and deep learning-based architectures which are then employed throughout this study by incorporating the novel algorithms for activity detection.