Paloghas's profile - activity

In my image recognition software I use ORB features and "findHomography" with RANSAC to validate my initial feature matches made by a Flannindex. With OpenCV 3 I consider to switch to AKAZE features. Unfortunately my tests with AKAZE features point out, that the time consumption of queries with AKAZE features is al lot higher, than the time consumption when using ORB. Furthermore the matching results are notably worse. With ORB no false positive matches remain after the reranking with "findHomography" with RANSAC. AKAZE produces a lot false positives matches and the number of true positives matches is lower than number of true positives matches of ORB. Does anyone have experience with AKAZE features in combination with "findHomopgrahy?

Additionally is made some experiments with the PnP Ransac solver of OpenCV 3. But the results are not good, too. Is it sufficient to use the default parameters in this case?

I'm currently working on an image recognition software. At the moment I'm working with 2D planes and I use "findHomography" with RANSAC to validate the initial feature matches.

Next I want to use 3D point clouds. As I understand from the online documentation of "findHomography" it is not applicable to 3D points. My question is, what is the best way to validate the feature matches of 3D point clouds? Can use "estimateAffine3D"? What do I have to consider, when I move from 2D to 3D images?