Ask Your Question
0

Detecting truck wheels

asked 2014-03-17 12:01:12 -0500

updated 2014-03-17 12:09:33 -0500

berak gravatar image

Hi, i am currently working on a projet which we have a set of photos of trucks going by a camera. I need to detect what type of truck it is (how many wheels it has). So i am using EMGU to try to detect this.

Problem i have is i cannot seem to be able to detect the wheels using EMGU's HoughCircle detection, it doesnt detect all the wheels and will also detect random circles in the fooliage.

So i dont know what i should try next, i tried implementing SURF algo to match wheels between them but this does not seem to work either since they arent exactly the same, is there a way i could implement a "loose" SURF algo ?

This is what i start with.

original

This is what i get after the Hough Circle detection. Many erroneous detections, has some are not even close to having a circle and the back wheels are detected as a single one for some reason.

Hough Circles

Would it be possible to either confirm that the detected circle are actually wheels using SURF and matching them between themselfs ? I am a bit lost on what i should do next, any help would be greatly appreciated.

(sorry for the bad english)

edit retag flag offensive close merge delete

Comments

You can have a few templates of wheels and search for the those templates in the image using SURF. Would that work for you?

GilLevi gravatar imageGilLevi ( 2014-03-18 09:55:15 -0500 )edit

1 answer

Sort by » oldest newest most voted
0

answered 2015-03-14 08:33:39 -0500

Hi Denjizz… Did you try other platforms like IM Raste, PBMPLUS, Img Software Set etc? If not then you should try once.

If you want to detect wheels of truckand unable to do via EMGU then I think you should put your question on EMGU discussion board (i.e. http://www.emgu.com/forum/) or support. Their expert would more efficiently be able to answer the actual cause of this issue.

edit flag offensive delete link more
Login/Signup to Answer

Question Tools

Stats

Asked: 2014-03-17 12:01:12 -0500

Seen: 839 times

Last updated: Mar 17 '14