Estimate optical flow



flow = estimateFlow(opticFlow,I) estimates optical flow between two consecutive video frames.


collapse all

Create a VideoReader object for the input video file, visiontraffic.avi. Specify the timestamp of the frame to read as 11.

vidReader = VideoReader('visiontraffic.avi','CurrentTime',11);

Specify the optical flow estimation method as opticalFlowHS. The output is an object specifying the optical flow estimation method and its properties.

opticFlow = opticalFlowHS
opticFlow = 
  opticalFlowHS with properties:

            Smoothness: 1
          MaxIteration: 10
    VelocityDifference: 0

Create a custom figure window to visualize the optical flow vectors.

h = figure;
hViewPanel = uipanel(h,'Position',[0 0 1 1],'Title','Plot of Optical Flow Vectors');
hPlot = axes(hViewPanel);

Read image frames from the VideoReader object and convert to grayscale images. Estimate the optical flow from consecutive image frames. Display the current image frame and plot the optical flow vectors as quiver plot.

while hasFrame(vidReader)
    frameRGB = readFrame(vidReader);
    frameGray = rgb2gray(frameRGB);  
    flow = estimateFlow(opticFlow,frameGray);
    hold on
    plot(flow,'DecimationFactor',[5 5],'ScaleFactor',60,'Parent',hPlot);
    hold off

Input Arguments

collapse all

Object for optical flow estimation, specified as one of the following:

The input opticFlow defines the optical flow estimation method and its properties used for estimating the optical flow velocity matrices.

Current video frame, specified as a 2-D grayscale image of size m-by-n. The input image is generated from the current video frame read using the VideoReader object. The video frames in RGB format must be converted to 2-D grayscale images for estimating the optical flow.

Output Arguments

collapse all

Object for storing optical flow velocity matrices, returned as an opticalFlow object.


The function estimates optical flow of the input video using the method specified by the input object opticFlow. The optical flow is estimated as the motion between two consecutive video frames. The video frame T at the given instant tcurrent is referred as current frame and the video frame T-1 is referred as previous frame. The initial value of the previous frame at time tcurrent = 0 is set as a uniform image of grayscale value 0.


If you specify opticFlow as opticalFlowLKDoG object, then the estimation delays by an amount relative to the number of video frames. The amount of delay depends on the value of NumFrames defined in opticalFlowLKDoG object. The optic flow estimated for a video frame at tcurrent corresponds to the video frame at time tflow=(tcurrent(NumFrames1)/2). tcurrent is the time of the current video frame.

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

See Also

Introduced in R2015a