2

I came across GridAdaptedFeatureDetector as an interface to feature detector in opencv. I was under the impression that we could use this to say partition an image into NxM cells and detect features for each cell. But I can't find documentation nor can I understand the source code for this interface.

Could someone let me know if GridAdaptedFeatureDetector can detect features by partitioning an image and returning image descriptors per cell? Or is there another method I could use to detect features in each cell individually?

Thanks!

user3500124
  • 63
  • 1
  • 5

1 Answers1

0

Yes, GridAdaptedFeatureDetector partitions image into cells and detect features for each cell. This functionality is available only in OpenCV2. Here is the documentation.

However, you might be interested in a recent paper that tackles the problem of homogeneous keypoint distribution on the image. C++, Python, and Matlab interfaces are provided in this repository.

Alex Bailo
  • 197
  • 2
  • 15