Splitting a similar object in an image - opencv python

Question

I am trying to detect objects in an image that look like a reference image. Here is how I am trying to do this:

Here is an example image:

and here is the image with the SURF key points:

The rectangle is drawn based on a clustering method such as Hierarchical Clustering.

The main problem is that in this case it does not detect objects separately, it discovers everything as one object.

Is there a way to separate these key points in order to detect each car separately? This is a good way to detect objects, or if there is a better way, please suggest.

Answer 1

SURF key points are useful for detecting similar images or images taken from the same place from different angles. Although you can use Haar classifiers for object detection purposes. It is also part of the OpenCV library.

Here 's another great tutorial on finding objects using OpenCV.