Journals Proceedings

Abstract

The main objective of my paper is to propose a new spatio temporal gait representation scheme to characterize human walking properties for individual recognition by gait in a single camera-based setup. In the proposed method, width vector of outer contour of binary silhouette and ART (Angular Radial Transform) coefficients are taken as the feature vector. PCA is applied to remove correlation between the features and also to reduce its dimensionality of the features. These extracted feature vectors are used to recognizing the individuals. Hidden Markov Model (HMM) is used to recognize the individual. Some intermediate experimental results shows the effectiveness of proposed system.