Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

Object tracking using cross correlation

download source code


Cross correlation is a standard method of estimating the degree to which two series are correlated.Once the
straightforward representation for digital images is a two-dimensional signal, which are generally the outputs of
two-dimensional systems, we need the mathematical concepts used in the study of such systems.
A digital image can be represented as a two dimensional matrix. Its elements are called pixels and to each
pixel it is associated a color intensity or a grey-level value. In the case of color images, an usual color system is
the RGB one.

if two images are cross-correlated then the resultant signal results a peak where there is higher similarity. the location of the peak is the location of the object.

This is my simple experiment in Matlab


download source code
imreg3.jpg


[video=youtube;juvza_AzkHI]https://www.youtube.com/watch?feature=player_embedded&v=juvza_AzkHI#t=0s[/video]
download source code

Comments

Congratulations to the Intersting example,


However It was not clear to me what feature of image was used to match.
Due cross-correlation algorithm is stronghly scale and inclination dependent, I sugest you to implement the SURF algorithm.

+++
 

Part and Inventory Search

Blog entry information

Author
sagar474
Read time
1 min read
Views
821
Comments
2
Last update

More entries in Uncategorized

More entries from sagar474

Share this entry

Back
Top