-1

I am working on the blind man navigation project. for this i need to detect right and left arrows using open cv and python. can anyone help with procedure or with sample code. i am pretty much new to open cv I have to detect the following shape:

enter image description here

This will be in a live environment i.e. the arrow will be printed on a piece of A4 paper and hung up in a corridor. The camera which needs to detect the image will most likely be a bit shaky so there will be some deformation of the image I presume, also lighting might be an issue. Further the arrow only needs to be detected from the front e.g. not from the side where it will be deformed.

I am now wondering now what my best approach might be to correctly detect the arrow and as such its direction, left or right.

2
  • Please add more details, and some images... Now it's totally unclear what you're asking Commented Apr 7, 2016 at 11:44
  • 1
    Does this answer your question? How to detect different types of arrows in image? Commented Apr 17, 2022 at 21:10

1 Answer 1

1
  1. You can use template matching to detect the arrow, however if you using handheld camera, then to get the direction right, you need to make sure that the camera pose is correct, that is the camera is not rotated.

  2. You can use feature based classifier such as HOG or Corners, Lines etc to build a detector and later predict the direction.

This Paper parents a road sign detection approach which is applicable in your case.

Sign up to request clarification or add additional context in comments.

2 Comments

Template matching is not working. Can you suggest the algorithm for detection
Maybe that is due to scale changes. You should try Gaussian Pyramid and do matching on the pyramid images. However this will be computationally expensive.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.