{"id":13440127,"url":"https://github.com/kuixu/kitti_object_vis","last_synced_at":"2025-05-16T12:08:04.991Z","repository":{"id":38409772,"uuid":"138973288","full_name":"kuixu/kitti_object_vis","owner":"kuixu","description":"KITTI Object Visualization (Birdview, Volumetric LiDar point cloud )","archived":false,"fork":false,"pushed_at":"2022-02-04T07:01:45.000Z","size":11511,"stargazers_count":1102,"open_issues_count":29,"forks_count":235,"subscribers_count":14,"default_branch":"master","last_synced_at":"2025-04-12T06:15:09.421Z","etag":null,"topics":["3d-object-detection","birdview","kitti-dataset","lidar-point-cloud","visualization"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kuixu.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-06-28T06:02:31.000Z","updated_at":"2025-04-11T10:07:28.000Z","dependencies_parsed_at":"2022-07-12T17:29:00.535Z","dependency_job_id":null,"html_url":"https://github.com/kuixu/kitti_object_vis","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuixu%2Fkitti_object_vis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuixu%2Fkitti_object_vis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuixu%2Fkitti_object_vis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kuixu%2Fkitti_object_vis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kuixu","download_url":"https://codeload.github.com/kuixu/kitti_object_vis/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248525138,"owners_count":21118619,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["3d-object-detection","birdview","kitti-dataset","lidar-point-cloud","visualization"],"created_at":"2024-07-31T03:01:20.011Z","updated_at":"2025-04-12T06:15:19.398Z","avatar_url":"https://github.com/kuixu.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# KITTI Object data transformation and visualization\n\n\n\n## Dataset\n\nDownload the data (calib, image\\_2, label\\_2, velodyne) from [Kitti Object Detection Dataset](http://www.cvlibs.net/datasets/kitti/eval_object.php?obj_benchmark=3d) and place it in your data folder at `kitti/object`\n\n\nThe folder structure is as following:\n```\nkitti\n    object\n        testing\n            calib\n               000000.txt\n            image_2\n               000000.png\n            label_2\n               000000.txt\n            velodyne\n               000000.bin\n            pred\n               000000.txt\n        training\n            calib\n               000000.txt\n            image_2\n               000000.png\n            label_2\n               000000.txt\n            velodyne\n               000000.bin\n            pred\n               000000.txt\n```\n\n## Install locally on a Ubuntu 16.04 PC with GUI\n- start from a new conda enviornment:\n```\n(base)$ conda create -n kitti_vis python=3.7 # vtk does not support python 3.8\n(base)$ conda activate kitti_vis\n```\n- opencv, pillow, scipy, matplotlib\n```\n(kitti_vis)$ pip install opencv-python pillow scipy matplotlib\n```\n- install mayavi from conda-forge, this installs vtk and pyqt5 automatically\n```\n(kitti_vis)$ conda install mayavi -c conda-forge\n```\n- test installation\n```\n(kitti_vis)$ python kitti_object.py --show_lidar_with_depth --img_fov --const_box --vis\n```\n\n**Note: the above installation has been tested not work on MacOS.**\n\n## Install remotely\nPlease refer to the [jupyter](jupyter/) folder for installing on a remote server and visulizing in Jupyter Notebook.\n\n## Visualization\n\n1. 3D boxes on LiDar point cloud in volumetric mode\n2. 2D and 3D boxes on Camera image\n3. 2D boxes on LiDar Birdview\n4. LiDar data on Camera image\n\n\n```shell\n$ python kitti_object.py --help\nusage: kitti_object.py [-h] [-d N] [-i N] [-p] [-s] [-l N] [-e N] [-r N]\n                       [--gen_depth] [--vis] [--depth] [--img_fov]\n                       [--const_box] [--save_depth] [--pc_label]\n                       [--show_lidar_on_image] [--show_lidar_with_depth]\n                       [--show_image_with_boxes]\n                       [--show_lidar_topview_with_boxes]\n\nKIITI Object Visualization\n\noptional arguments:\n  -h, --help            show this help message and exit\n  -d N, --dir N         input (default: data/object)\n  -i N, --ind N         input (default: data/object)\n  -p, --pred            show predict results\n  -s, --stat            stat the w/h/l of point cloud in gt bbox\n  -l N, --lidar N       velodyne dir (default: velodyne)\n  -e N, --depthdir N    depth dir (default: depth)\n  -r N, --preddir N     predicted boxes (default: pred)\n  --gen_depth           generate depth\n  --vis                 show images\n  --depth               load depth\n  --img_fov             front view mapping\n  --const_box           constraint box\n  --save_depth          save depth into file\n  --pc_label            5-verctor lidar, pc with label\n  --show_lidar_on_image\n                        project lidar on image\n  --show_lidar_with_depth\n                        --show_lidar, depth is supported\n  --show_image_with_boxes\n                        show lidar\n  --show_lidar_topview_with_boxes\n                        show lidar topview\n  --split               use training split or testing split (default: training)\n\n```\n\n```shell\n$ python kitti_object.py\n```\nSpecific your own folder,\n```shell\n$ python kitti_object.py -d /path/to/kitti/object\n```\n\nShow LiDAR only\n```\n$ python kitti_object.py --show_lidar_with_depth --img_fov --const_box --vis\n```\n\nShow LiDAR and image\n```\n$ python kitti_object.py --show_lidar_with_depth --img_fov --const_box --vis --show_image_with_boxes\n```\n\nShow LiDAR and image with specific index\n```\n$ python kitti_object.py --show_lidar_with_depth --img_fov --const_box --vis --show_image_with_boxes --ind 1 \n```\n\nShow LiDAR with `modified LiDAR file` with an additional point cloud label/marker as the 5th dimention(5 vector: x, y, z, intensity, pc_label). (This option is for very specific case. If you don't have this type of data, don't use this option).\n```\n$ python kitti_object.py --show_lidar_with_depth --img_fov --const_box --vis --pc_label\n```\n\n## Demo\n\n#### 2D, 3D boxes and LiDar data on Camera image\n\u003cimg src=\"./imgs/rgb.png\" alt=\"2D, 3D boxes LiDar data on Camera image\" align=\"center\" /\u003e\n\u003cimg src=\"./imgs/lidar-label.png\" alt=\"boxes with class label\" align=\"center\" /\u003e\nCredit: @yuanzhenxun\n\n#### LiDar birdview and point cloud (3D)\n\u003cimg src=\"./imgs/lidar.png\" alt=\"LiDar point cloud and birdview\" align=\"center\" /\u003e\n\n## Show Predicted Results\n\nFirstly, map KITTI official formated results into data directory\n```\n./map_pred.sh /path/to/results\n```\n\n```python\npython kitti_object.py -p --vis\n```\n\u003cimg src=\"./imgs/pred.png\" alt=\"Show Predicted Results\" align=\"center\" /\u003e\n\n\n## Acknowlegement\n\nCode is mainly from [f-pointnet](https://github.com/charlesq34/frustum-pointnets) and [MV3D](https://github.com/bostondiditeam/MV3D)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkuixu%2Fkitti_object_vis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkuixu%2Fkitti_object_vis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkuixu%2Fkitti_object_vis/lists"}