Human Activity Recognition Using Local Motion Histogram

Abstract

Human activity recognition is an important problem in computer vision with multiple challenges. In this paper we have proposed a method for human activity recognition based on local estimation of motion in RGB videos. Background subtraction method is used on pair of consecutive frames to determine local motion, and for a small bundle of frames, the maximum magnitude of motion at a pixel is utilized to create a Projected Motion Matrix. The matrix is segmented into horizontal and vertical strips and binned histograms of each strip serve as feature descriptors. We have used these descriptors in a random forest based classification scheme and evaluated the performance on JHMDB, a publicly available human action RGB dataset. © Springer Nature Singapore Pte Ltd. 2018.