Documentation

This is machine translation

Translated by Microsoft
Mouseover text to see original. Click the button below to return to the English version of the page.

Note: This page has been translated by MathWorks. Click here to see
To view all translated materials including this page, select Country from the country navigator on the bottom of this page.

Live Motion Detection Using Optical Flow

This example shows how to create a video algorithm to detect motion using optical flow technique.This example uses the Image Acquisition Toolbox™ System Object along with Computer Vision System Toolbox™ System objects.

Introduction

This example streams images from an image acquisition device to detect motion in the live video. It uses the optical flow estimation technique to estimate the motion vectors in each frame of the live video sequence. Once the motion vectors are determined, we draw it over the moving objects in the video sequence.

Initialization

Create the Video Device System object.

vidDevice = imaq.VideoDevice('winvideo', 1, 'YUY2_320x240', ...
                             'ReturnedColorSpace', 'rgb', ...
                             'DeviceProperties.Brightness', 130, ...
                             'DeviceProperties.Sharpness', 50);

Create a System object to estimate direction and speed of object motion from one video frame to another using optical flow.

opticFlow = opticalFlowHS;

Stream Acquisition and Processing Loop

Create a processing loop to perform motion detection in the input video. This loop uses the System objects you instantiated above.

% Set up for stream
nFrames = 0;
while (nFrames<100)     % Process for the first 100 frames.
    % Acquire single frame from imaging device.
    frameRGB = vidDevice();

    % Compute the optical flow for that particular frame.
    flow = estimateFlow(opticFlow,rgb2gray(frameRGB));

    imshow(frameRGB)
    hold on
    plot(flow,'DecimationFactor',[5 5],'ScaleFactor',25)
    hold off

    % Increment frame count
    nFrames = nFrames + 1;
end

Summary

In the figure window, you can see that the example detected the motion of the black file. The moving objects are represented using the vector field lines as seen in the image.

Release

Here you call the release method on the System objects to close any open files and devices.

release(vidDevice);
Was this topic helpful?