Prev: NNz won't take a 160-by-120 binary image??
Next: create signal block
From: prachi on 7 Feb 2010 06:15
http://www.dspdesignline.com/howto/210000460
check this out...might help u!
From: Ongun Palaoglu on 14 Feb 2010 21:06
Hi there, I am working on motion detectionas well for my senior design project. Currently I am working on a prerecorded video file. I used http://www.mathworks.ch/matlabcentral/newsreader/view_thread/171190 , this code to normalize the image. I have only one image now, I am using a black circle which is moving in the screen for motion.

Can someone explain me those steps little more detailed.

**Convert to Normalized RGB to remove the effect of illumination variation.

After the code, on the link, picture should be RGB. how am i going to remove the effect of illumination variation. Before that what is the effect of illumination variation?

** Over a protracted period, with no moving target in the scene, calculate the mean background intensity of each individual pixel, together with its associated standard deviation.

Is this for threshold? If something moves it will change the mean value?

** Select a confidence level (e.g. 3xsigma) whereby the difference between the mean image and the current image is deemed to be statistically similar - note that regions that are naturally liable to change (e.g. trees moving) will have a very high sigma, and will consequently be very tolerant of any changes in the scene.

For this part, I add t=1-10 backgrounds and take the mean value of it. I understand the reason. Is the confididence level is teh same as previous threshold?

Thanks a lot
 | 
Pages: 1
Prev: NNz won't take a 160-by-120 binary image??
Next: create signal block