Human Activity and Gesture Recognition: A Review

Abstract

Human activity recognition is the method of extracting and predicting the movements of the human body often indoors by using any hardware device such as a camera or sensor-based device. At an earlier stage collecting data from sensors is quite expensive but recently we have smartphones and other personal devices which have accelerometer-based sensors that track our activities. HAR is a classification method in which people have a great interest because we can find different actions of the human body like sitting, walking, running, jumping, jogging etc. by using body-worn sensors like accelerometer, gyroscope and applying methods like convolution neural network and other deep learning methods. The main objective of this review is to study different human activities, compounds and methods that are used to recognize actions and position of the body.