Gait Recognition Underground Coal Mine by Combining Wavelet Packet Transforms and Principle Component Analysis

摘要

Due to the video light underground coal mine is gloomy and not uniform, and lack the color contrast information, target and background is similar, the human motion detection and segmentation is difficult to process quickly. It is still a difficult problem to design a target detection and segmentation model of dynamic human body in the complex environment underground coal mine. A gait recognition method by combining wavelet packet transforms (WPT) and principle component analysis (PCA) is proposed in this paper. The proposed method includes the following steps, gait sequence pretreatment, feature extraction by WPT and dimensionality reduction by PCA and classifying the test samples by the nearest neighbor classifier. The experiment results on the public gait database show the effectiveness of the proposed method.