A Method for Human Gait Recognition from Video Streams Using Silhouette, Height and Step Length

摘要

This paper proposes and presents one way for people recognition from video streams. People recognition can be realized using various biometric features, behavioral or physiological, and methods based on that features. This work proposes and describes an algorithm for people recognition from video streams that is composed of two modules, module for dataset creation and module for recognition. Module for dataset creation involves creation of various types of person images and parameters. Module for recognition includes multiple comparisons of the images and different parameters comparison. These parameters are average height and average step length of a person during a gait cycle. For experimental purposes, a dataset for 15 persons in gait is created using a long-range stereo camera in outdoor environment. The algorithm has high accuracy in people recognition and easily can be upgraded with additional steps and modules, so it is suitable for use in various applications.