Jens Behley

icon indicating a website link https://jbehley.github.io/

icon company University of Bonn icon location Bonn, Germany icon location Post-doctoral Researcher at the Department of Photogrammetry, University of Bonn.

Results 106 comments of Jens Behley

Question about speed after tensorrt of rangenet++

sorry, I cannot answer this. we have currently also no one looking into this.

About learning_map in semantic-kitti.yaml file

the learning_map converts the original SemanticKITTI format, e.g., 10, 20, etc., into the 0,1,2,3,... labels used for learning. (Therefore, there are multiple labels mapped to "other-vehicle", like busses, etc.) The...

IndexError: index -2147483648 is out of bounds for axis 0 with size 64

sorry for the late reply. it's hard to debug what it's happening there, but something in the projection does produce a strange y coordinate. I would try to check if...

IndexError: index -2147483648 is out of bounds for axis 0 with size 64

Does this solve your issue, @Trexzhou?

If it's possible to update the octree?

Currently, this is not supported. The main reason is that this would require to modify the successor list on which we rely to assign each octant the points it contains....

Removal of single points

Thanks for the comment, but currently I'm busy with quite different stuff. At least, the other neighbor queries are partially already done: nearest neighbor. k nearest neighbors is also sometimes...

Removal of single points

Lately, I had a lot of other stuff to do, so I had not time to look into this issue. However, if I get your idea right, it would somehow...

Performance improvements replacing std::pow( float, 2 ) with explicit squaring, std::array<uint32_t,8> in createOctant

Thanks for your sharing your observations under Windows and glad to hear that my implementation also works there. Did you encounter any other issues when porting the code to windows?...

Performance improvements replacing std::pow( float, 2 ) with explicit squaring, std::array<uint32_t,8> in createOctant

Thanks again for your comment. I put the changes on my TODO list and hopefully can return to this issue soon. Good luck with your project and glad to hear...

Extend to find closest N neighbors

my octree relies on knowing the maximum possible radius and therefore i can just stop descending if I find an octant that is inside the search ball. for k nearest...