Computer Vision Demonstration Website

Electronics and Computer Science
University of Southampton

Optical Flow

Optical flow is a technique used to describe image motion. It is usually applied to a series of images that have a small time step between them, for example, video frames. Optical flow calculates a velocity for points within the images, and provides an estimation of where points could be in the next image sequence.

How it works

There are many different approaches to optical flow, the method demonstrated above is known as area correlation optical flow.

Area correlation optical flow works by pairing points in one image to points in the next. Point matching is done by comparing intensities within a given window, and pairing points that have the smallest difference in intensity. Once points have been paired, the velocity is calculated as the distance that the point has moved. To reduce the number of calculations required the maximum displacement of a point can be set.

Code

Image processing classes:

• opticalFlow.java

Demo framework:

• flowDemo.java

The pages were designed and developed for educational purposes only, to demonstrate how computer vision techniques work. They are designed for no other purpose and neither the authors nor their institutions accept any liability concerning use of these pages.

Links

Mark Nixon & Alberto Aguado, 2002, Feature Extraction & Image Processing, Newnes

ECS | Feature Extraction & Image Processing | © 2005 University of Southampton