An optical flow based approach for action recognition

Abstract

A new approach for motion-based representation on the basis of optical flow analysis and random sample consensus (RANSAC) method is proposed in this paper. 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. It is intuitive that an action can be characterized by the frequent movement of the optical flow points or interest points at different areas of the human figure. Additionally, RANSAC, an iterative method to estimate parameters of a mathematical model from a set of observed data which contains inliers and outliers, can be used to filter out any unwanted interested points all around the scene and keep only those which are related to the particular human's motion. By this manner, the area of the human body within the frame is estimated and this rectangular area is segmented into a number of smaller regions or blocks. The percentage of change of interest points in each block from frame to frame is then recorded. Similar procedure is repeated for different persons performing the same action and the corresponding values are averaged for respective blocks. A matrix constructed by this strategy is used as a feature vector for that particular action. Afterwards, for the purpose of recognition using the extracted feature vectors, a distance-based similarity measure and a support vector machine (SVM)-based classification technique have been exploited. From extensive experimentations upon a standard motion database, itis found that the proposed method offers not only a very high degree of accuracy but also computational savings.

Efficient Hardware Implementation of the Horn-Schunck Algorithm for High-Resolution Real-Time Dense Optical Flow Sensor

“…It allows to extract the object movement direction and its speed [ 2 ]. It can also be used for classification of pixels according to their motion flow (for example in [ 3 ] rigid bodies such as cars were differentiated from people based on this premise). Moving object mask [ 4 , 5 ] can be obtained by thresholding the optical flow magnitude.…”

Temporal segmentation of gestures using gradient orientation of depth images

“…[20] Given N -dimensional feature vector for the class i of the m-th sample depth image are γ m (1), γ m (2), ..., γ m (N ) and the t-th test sample depth image frame with a feature vector κ t (1), κ t (2), ..., κ t (N ), a similarity measure between the t-th test sample of the unknown class and the depth image of the class i is defined as…”

A Comparative Study of different Oject Tracking Methods in a Video

“…The method which makes use of pattern of the apparent object motion and edges in video sequences based on relative motion between an observer and the scene is known as optic flow [15]. This method works by calculating the image optical flow field and carrying out clustering based on image optical flow distribution characteristics.…”