Re: Advise on object detection
- From: serg271 <serg271@xxxxxxxxx>
- Date: Wed, 21 May 2008 22:59:46 -0700 (PDT)
On May 21, 11:35 am, stormogulen <bjarn...@xxxxxxxxx> wrote:
Hi all,
I have a bunch of pictures like this one:
(http://cid-1627b3c28e2dc281.spaces.live.com/photos/cns!
1627B3C28E2DC281!125 )
(A picture of rocks with soil between them)
I would like to detect and extract every single rock in the picture.
What would be the best way to do this? I have tried using Canny edge
detection to find each rock, but even though the contrast between rock
and soil is quite high, I don't get all the edges in the picture.
Also I would like to find the green box which is somewhere at the
center of the picture. How would you suggest that I do that?
Best regards,
Bjarne
Adaptive thresholding should do the trick, using intensity histogram
for example. The rocks considerably lighter then ground, and there is
no lightning gradient so single histogram could be enough. Binarize
the image and after that count white connected components.
Green box you can probably find making adaptive thresholding on hue
and saturation.
.
- References:
- Advise on object detection
- From: stormogulen
- Advise on object detection
- Prev by Date: Re: Advise on object detection
- Next by Date: PCI Frame Grabber in Medical Imaging
- Previous by thread: Re: Advise on object detection
- Next by thread: Re: Advise on object detection
- Index(es):
Relevant Pages
|
|