Skip to Main Content
This paper proposes a novel approach towards human action recognition based on optical flow and random sample consensus (RANSAC) by utilizing frequency domain feature extraction. Action representations can be considered as image templates, which can be useful for understanding various actions or gestures as well as for recognition and analysis. Optical flow is the pattern of apparent motion of objects, surfaces, and edges in a visual scene caused by the relative motion between an observer (an eye or a camera) and the scene. Additionally, RANSAC is an iterative method to estimate parameters of a mathematical model from a set of observed data, which contains inliers and outliers. The proposed scheme employs optical flow to determine the motion of humans. Human motions are further localized and identified using RANSAC. Feature extraction for the purpose of action recognition is performed in frequency domain. It has been shown that the use of frequency domain features enhances the distinguishability of different actions and certain undesirable phenomena, such as camera movement and change in camera distance from the subject, are less severe in the frequency domain. Principal component analysis is performed to further reduce the dimensionality of the feature space. Extensive experimentations have been carried out upon some standard motion databases. It is found that the proposed method offers not only computational savings but also a very high degree of accuracy.