zhoupengwei / tloam Goto Github PK

Hi, thanks for sharing your work! I have installed the open3d success. But, when I compile the code, I encounter the following problem. Can you give me some advices, thank you!

error: ‘open3d::geometry::OrientedBoundingBox open3d::geometry::PointCloud2::GetOrientedBoundingBox() const’ marked ‘override’, but does not override
64 | OrientedBoundingBox GetOrientedBoundingBox() const override;
| ^~~~~~~~~~~~~~~~~~~~~~
In file included from ~/tloam_ws/src/tloam/include/tloam/subscriber/cloud_subscriber.hpp:21,
from ~/tloam_ws/src/tloam/src/subscriber/cloud_subscriber.cpp:10:
~/tloam_ws/src/tloam/include/tloam/models/utils/sensor_data.hpp: In member function ‘void tloam::CloudData::reset()’:
~/tloam_ws/src/tloam/include/tloam/models/utils/sensor_data.hpp:24:43: error: invalid new-expression of abstract class type ‘open3d::geometry::PointCloud2’
24 | cloud_ptr.reset(new open3d::geometry::PointCloud2);

Can your provide a docker image for Tloam?

hi,the work is excellent.But when I set up the open3d 0.12.0 environment, I used cuda9.0 and kept reporting errors. The content is as follows. Does the 0.12.0 version support cuda9.0?
CMake Error at /home/zhangcz/third_parts/cmake-3.18.0-Linux-x86_64/share/cmake-3.18/Modules/CMakeDetermineCUDACompiler.cmake:552 (message):
The CMAKE_CUDA_ARCHITECTURES:
75-real
do not all work with this compiler. Try:
30
instead.

关于这里地面法向量的计算，我没有太弄懂，为什么会计算三个主轴向量（代表的物理意义是什么？）后面的权重累和又代表什么？

Hi,zpw,
Thanks for sharing the great jobs.
I have a question about the code and the paper?
I can't find the dynamic filter partion in the code ,as you said "filter out the tiny groups and potential dynamic objects" in the |||-C of the paper. Maybe I missed something, can you give me some advice?

Thanks again!

您好，在编译时出现这个错误，不知道怎么解决，谢谢

Hi, dear author，it's a great job
What evaluation tools are used to obtain the parameters(relative translational error in%/relative error in degrees per 100m) in the paper. I hope you can teach me. Thank you very much.

The results of your kitti experiment do not match those of other papers, and the accuracy of FLOAM and ALOAM is much higher than the results written in your paper

Thank you for sharing the code, the work is interesting.

I am wondering if you have a script to lunch the code without using ROS?