url-kaist / travel Goto Github PK

The sum of ground points and non-ground points is not equal to the number of points in the original point cloud.

For example, seq 00, frame 0
raw pc size: 124668
travel:
pc_ground size: 75306
pc_non_ground size: 53565
sum: 128871
where 128871 > 124668

The code shows a segfault on the ros::spin() when using the rough_terrain_2.bag.

While debugging I commented all code minus the callback body and now I believe there is some kind of problem or mismatch with the node msg and the rosbag.

I made the docker work perfectly fine.

de.h: 没有那个文件或目录
#include "travel/node.h"
您好，在您的仓里面没有头文件，可以发一下吗谢谢

Is it possible to build this package on ros noetic version?
I have a build error "fatal error: travel/node.h: No such file or directory"
Thank you!

Thanks for your great work. I am currently working on a new clustering method, and want to use the Evaluation Metrics, OSE and USE, proposed in your paper. But I run into some problem when implementing it. Could you share this part of code. I need to use the labels generated by clustering algorithm to calculate the corresponding evaluation metrics.

Thanks for your work.
I used the same color to represent the point with the same ring number, but the result was not correct. The function getRowIdx() seems not very accurate. I think the reason is the distortion of lidar. Besides, I think horz_scan of semantic kitti dataset should be 2048 instead of 4500.

Thanks for your open source. The debug code seems to be incompleted. Noted that some related code has been commented. After uncomment these code, I still can not get the right result. I wonder if this part hasn't been completed yet.