How to detect darts on a dart board using Computer Vision in OpenCV? [closed]

Question

As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, visit the help center for guidance.

Closed 9 years ago.

I'm a newbie to the world of Computer Vision. Here's what I need to do. Given an image, pick out and draw a circle around all the locations in the image which contain an object A. In other words, say there are 3 darts on a shooting board and I want to return the locations of them. How would I do this using OpenCV? What's the name of the technique(s) I would have to use. I want to know what parts of the library to get familiar with in order to implement this feature.

Answer 1

So this tutorial seems to cover some of the basic topics. You should look for pattern recognition, edge detection... I do not know if you will be working with static images, or video. A mix of techniques can be combined, and the robustness of the method depends on how much time you can spend processing the given image/frame.

To draw stuff on the image its pretty simple, for example a circle is a simple function call with a few parameters.

I am no expert in this matters, but I'd you can start with a static image and draw some circles, then look for a way to detect your pattern (for example, to extract image properties you can look into SURF)

Also if you have access to Matlab, it can perform some image processing.

Answer 2

Well if you have static camera, shooting from same place you can take a shot beforehand, without darts. And the just do a diff between image without darts and with them. At the place with darts there will be distinctive difference.

Some morphological operations on the diff image should take care of noise.

Answer 3

You should review the appropriate literature to get a background in the problem field, which in this case is probably object recognition and detection.

A good reference is Szeliski's CV book or any other material your lecturer can recommend you. In Szeliski's book see Chapter 14.

The whole subject is certainly not trivial and just jumping into OpenCV won't help you too much without understanding the theoretical background. In anycase here is interesting example using SURF.