Download All

Code covered by the BSD License  

Highlights from
Affine optic flow

5.0

5.0 | 2 ratings Rate this file 52 Downloads (last 30 days) File Size: 500.22 KB File ID: #27093
image thumbnail

Affine optic flow

by David Young

 

26 Mar 2010 (Updated 09 Dec 2011)

Estimates the parameters of an affine (first-order) optic flow model from two images.

| Watch this File

File Information
Description

An affine (or first-order) optic flow model has 6 parameters, describing image translation, dilation, rotation and shear. The class affine_flow provides methods to estimates these parameters for two frames of an image sequence.

The class implements a least-squares fit of the parameters to estimates of the spatial and temporal grey-level gradients. This is an extension of the well-known Lucas-Kanade method. The images are either sampled conventionally, on a rectilinear grid, or on a log-polar grid. In the latter case, the class may iteratively refine its estimates by moving the sampling grid to track the motion. Options to specify a region of interest and smoothing and sampling parameters are provided.

The file includes a demonstration of the class, and test images for this. The functions for smoothing images and estimating gradients may be useful independently, and log-polar sampling functions are included (and are available separately in submission 27023).
Required Products Image Processing Toolbox
MATLAB release MATLAB 7.10 (2010a)
Tags for This File  
Everyone's Tags
Tags I've Applied
Add New Tags Please login to tag files.
Comments and Ratings (6)
07 Jul 2010 Glen Lichtwark  
25 Aug 2010 Alfian Abdul Halin

Hi. I tried to run the demo code (with Jpeg images)... and got this error (but i think its not due to the jpegs)...

??? Error: File: affine_flow.m Line: 1 Column: 10
A class definition must be in an "@" directory.
28 Aug 2010 David Young

Alfian: What Matlab version are you using? It may be the problem: this class uses the fairly recent Matlab OO system, and was tested in version 2010a.
26 Jan 2011 Alfian Abdul Halin

The time I ran this I was using MATLAB 2007... you think it might work if I use R2009a?

27 Jan 2011 David Young

The Matlab OOP capabilities were introduced with version 2008a, so yes, I think it should work with 2009a. It's worth trying, and if there are problems they should be minor ones that can be fixed. For example you may need to replace '~' as an unused argument or result with a variable name such as 'unused'.
26 Oct 2011 Michael

Works great!
Please login to add a comment or rating.
Updates
30 Mar 2010

Fixed bug in use of ROI, allowed ROI in conjunction with log-polar sampling, simplified gradient computation by using exindex, minor changes to demo.
09 May 2010

Changed from a function to a class, for more efficient application to image sequences. (Argument checking etc. can be moved outside a loop, and some intermediate computations can be saved for later use.)
09 Dec 2011

Fixed bug which caused error when sample step was greater than 1.

Minor corrections to comments.

Changed order of arguments in gsmooth2 and gradients_xyt.
Tag Activity for this File
Tag Applied By Date/Time
optic flow David Young 26 Mar 2010 10:32:19
optical flow David Young 26 Mar 2010 10:32:19
affine David Young 26 Mar 2010 10:32:19
logpolar David Young 26 Mar 2010 10:32:19
active vision David Young 26 Mar 2010 10:32:19
image motion David Young 26 Mar 2010 10:32:19
image analysis David Young 26 Mar 2010 10:32:19
foveal vision David Young 26 Mar 2010 10:32:19
image motion parul agrawal 31 Mar 2010 03:46:17
image processing David Young 10 May 2010 10:25:40
optical flow mp2 mon 20 Feb 2012 06:22:04

Contact us at files@mathworks.com