Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Nvblox pull request - New features: new lidar and camera models; different weighting functions, etc. #16

Open
wants to merge 59 commits into
base: public
Choose a base branch
from
Open

Nvblox pull request - New features: new lidar and camera models; different weighting functions, etc. #16

wants to merge 59 commits into from

Conversation

gogojjh
Copy link

@gogojjh gogojjh commented Dec 4, 2022

New Features

  • Support more general LiDAR models, like the Ouster128 and VLP64, whose measurements do not strictly follow the original lidar projection model: oslidar.(h/cpp)
  • Support the rectified camera model: camera_pinhole.(h/cpp)
  • Support the computation of a normal image in CUDA from a range image: image_operation.(h/cpp)
  • Support different ``weighting average'' methods in the TSDF integration and color integration: weight_function.h
  • Create fuser_rgbd.(h/cpp) and fuser_lidar.(h/cpp) to distinguish the integration with a RGBD sensor from a lidar
  • Add new datasets support: KITTI and FusionPortable. Testing results are reported in several README files

@gogojjh
add nvblox_interfer link to nvblox_datasets
e3d4098
@gogojjh
add output time explanation
0407275
@gogojjh
add oslidar_impl and test_oslidar
1c698a5
@gogojjh
write fusionportable.cpp: load depth_image and z_image, image_loader,…
d291130 
… oslidar_impl
@gogojjh
[executables] define virtual function
8f243f4
@gogojjh
[executables] define virtual function
679045b
@gogojjh
[executables] define virtual function
6d0f43d
@gogojjh
[executables] use OSLidar in TSDF integration and view_calculator
1839063
@gogojjh
[TSDF integration] add comments and meet problems in integration
73c5b18
@gogojjh
meet bugs in view_calculator
4a7f06d
@gogojjh
projective_tsdf_integrator and view_calculator: add cuda memory operator
4b40905
@gogojjh
correct the lidar model
2655077
@gogojjh
successfully run on FusionPortable dataset, but cannot get correct re…
ba0eea0 
…sults
@gogojjh
add fuser_lidar to split out camera-based integration and lidar-based…
3bb2b24 
… integration
@gogojjh
fix the angle calculation of oslidar_impl
b60df8e
@gogojjh
address the lidar_impl
0cc07a9
@gogojjh
add README
0e3dfb9
@gogojjh
compute the minimum and maximum angle of ouster
eaf5397
@gogojjh
fix the intrinsics of the OSLidar model, and successfully got TSDF re…
0e927c4 
…construction results
@gogojjh
add explanation of processing OSLidar in README.md
2cdfed7
@gogojjh
add explanation of processing OSLidar in README.md
59b86e4
@gogojjh
add color integration
975546a
@gogojjh
add color integration
147a3a9
@gogojjh
add different voxel update method
b3045ad
@gogojjh
add test_normal_image but not really fix
79e771e
@gogojjh
finish test_normal_image
01a991a
@gogojjh
add normal_image_computation but not finish
ac65cb4
@gogojjh
successfullly compile and run the computeNormalImage
6f72246
@gogojjh
add normal data retrieval
579d292
@gogojjh
add different voxel_dis_method
71c89c2
@gogojjh
add non-projective distance implementation, but not test
ef28f7e
@gogojjh
add non-projective distance implementation, and successfully test
84e1e3b
@gogojjh
add non-projective distance implementation, and successfully test
24ddbd9
@gogojjh
add non-projective distance implementation, and successfully test
0a530f6
@gogojjh
add obstacle_output_path, but not test
0472265
@gogojjh
add the output of obstacle map
efb8eb0
@gogojjh
add non-projective distance implementation, and successfully test
27dea7a
@gogojjh
add experimental results on 20220216_escalator_day and 20220226_campu…
4d1d1e1 
…s_road_day
@gogojjh
add experimental results on 20220216_escalator_day and 20220226_campu…
521cd80 
…s_road_day
@gogojjh
format the cuda/conversions
38726d0
@gogojjh
add the tsdf integration with the KITTI dataset
57b573c
@gogojjh
add the tsdf integration with the KITTI dataset
f2497f8
@gogojjh
[README.md] add data download link
d0c2b1e
@gogojjh
[weight averaging] fix the linear weight of voxel_dis_method=6
02680c4
@gogojjh
add test with dynamic objects
066eec5
@gogojjh
add comments in projective_color_integrator
cff7706
@gogojjh
add template function in color_integration
b6774fc
@gogojjh
add camera_pinhole
0daefec
@gogojjh
add kitti.cpp and parse camera file for kitti data
b80beba
@gogojjh
perform color integration in the KITTI odometry seq07
7a48111
@gogojjh
add kitti.cpp and parse camera file for kitti data
2ce1a3b
@gogojjh
add kitti.cpp and parse camera file for kitti data
b5b1d5d
@gogojjh
successfully compile and run tests files && modify jjiao->gogojjh
9433101
@gogojjh
successfully compile and run tests files && modify jjiao->gogojjh
5357622
@gogojjh
successfully compile and run tests files && modify jjiao->gogojjh
b97a44f
@gogojjh
update README.md: add the link of the KITTI and FusionPortable dataset
99e75e9
@gogojjh
update README.md: add the link of the KITTI and FusionPortable dataset
717ffa9
@gogojjh
update README.md: add the link of the KITTI and FusionPortable dataset
5717740
@hjxwhy
Copy link

hjxwhy commented Dec 17, 2022

Thanks for your development, but the test data URL seems not work, I can't download the data for testing.

@gogojjh
Copy link
Author

gogojjh commented Dec 17, 2022

Thanks for your reminder. Please check the new link: http://gofile.me/4jm56/AcbBNmBO8

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@gogojjh @hjxwhy