A comparison study on different crowd motion estimation algorithms using matlab

The optical flow describes the direction and time rate of pixels in a time sequence of two consequent images. A two-dimensional velocity vector, carrying information on the direction and the velocity of motion is assigned to each pixel in a given place in the picture. This article describes different motion detection methods, gives a brief illustration of the optical flow conception, and presents in details the Lucas-Kanade and Horn-Schunk algorithms for optical flow estimation and their implementation using MATLAB. © Springer Science+Business Media Singapore 2014.