查看文章

Human activity recognition (HAR) in live videos has become an important research topic in computer vision. RHA is widely used in different fields such as healthcare, robot learning, intelligent surveillance system, human computer interactions (HCI), and many more. Recognition of activities in live or normal videos include a huge amount of data are required to be processed that is why it is a tough task. In the recent decades, researchers have developed various models using artificial intelligence and especially deep learning (DL) with multiple input sensor paradigm. This paper provides a comprehensive review of recent models of deep learning for HAR based on input sensor paradigm, dataset, feature extraction from dataset, preprocessing of data, classification of input data, and accuracy.