koide3 / Ndt_omp
Licence: bsd-2-clause
Multi-threaded and SSE friendly NDT algorithm
Stars: ✭ 291
Projects that are alternatives of or similar to Ndt omp
Fast gicp
A collection of GICP-based fast point cloud registration algorithms
Stars: ✭ 307 (+5.5%)
Mutual labels: multithreading, point-cloud, pcl, registration
Lidar camera calibration
Light-weight camera LiDAR calibration package for ROS using OpenCV and PCL (PnP + LM optimization)
Stars: ✭ 133 (-54.3%)
Mutual labels: ros, point-cloud, pcl
Cupoch
Robotics with GPU computing
Stars: ✭ 225 (-22.68%)
Mutual labels: ros, point-cloud, registration
Pcl Ros Cluster Segmentation
Cluster based segmentation of Point Cloud with PCL lib in ROS
Stars: ✭ 123 (-57.73%)
Mutual labels: ros, point-cloud, pcl
cloud to map
Algorithm that converts point cloud data into an occupancy grid
Stars: ✭ 26 (-91.07%)
Mutual labels: point-cloud, ros, pcl
Depth clustering
🚕 Fast and robust clustering of point clouds generated with a Velodyne sensor.
Stars: ✭ 657 (+125.77%)
Mutual labels: ros, point-cloud, pcl
Point Cloud Filter
Scripts showcasing filtering techniques applied to point cloud data.
Stars: ✭ 34 (-88.32%)
Mutual labels: ros, point-cloud, pcl
Adaptive clustering
Lightweight and Accurate Point Cloud Clustering
Stars: ✭ 125 (-57.04%)
Mutual labels: ros, point-cloud
superpose3d
register 3D point clouds using rotation, translation, and scale transformations.
Stars: ✭ 34 (-88.32%)
Mutual labels: point-cloud, registration
pcl.py
Templated python inferface for Point Cloud Library (PCL) based on Cython
Stars: ✭ 64 (-78.01%)
Mutual labels: point-cloud, pcl
DeepI2P
DeepI2P: Image-to-Point Cloud Registration via Deep Classification. CVPR 2021
Stars: ✭ 130 (-55.33%)
Mutual labels: point-cloud, registration
YOHO
[ACM MM 2022] You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
Stars: ✭ 76 (-73.88%)
Mutual labels: point-cloud, registration
persee-depth-image-server
Stream openni2 depth images over the network
Stars: ✭ 21 (-92.78%)
Mutual labels: point-cloud, pcl
Awesome Robotic Tooling
Tooling for professional robotic development in C++ and Python with a touch of ROS, autonomous driving and aerospace.
Stars: ✭ 1,876 (+544.67%)
Mutual labels: ros, point-cloud
pcl-edge-detection
Edge-detection application with PointCloud Library
Stars: ✭ 32 (-89%)
Mutual labels: point-cloud, pcl
costmap depth camera
This is a costmap plugin for costmap_2d pkg. This plugin supports multiple depth cameras and run in real time.
Stars: ✭ 26 (-91.07%)
Mutual labels: point-cloud, ros
sp segmenter
Superpixel-based semantic segmentation, with object pose estimation and tracking. Provided as a ROS package.
Stars: ✭ 33 (-88.66%)
Mutual labels: point-cloud, ros
pcljava
A port of the Point Cloud Library (PCL) using Java Native Interface (JNI).
Stars: ✭ 19 (-93.47%)
Mutual labels: point-cloud, pcl
Ira laser tools
All laser type assemblers and manipulators.
Stars: ✭ 87 (-70.1%)
Mutual labels: ros, pcl
ndt_omp
This package provides an OpenMP-boosted Normal Distributions Transform (and GICP) algorithm derived from pcl. The NDT algorithm is modified to be SSE-friendly and multi-threaded. It can run up to 10 times faster than its original version in pcl.
Benchmark (on Core i7-6700K)
$ roscd ndt_omp/data
$ rosrun ndt_omp align 251370668.pcd 251371071.pcd
--- pcl::NDT ---
single : 282.222[msec]
10times: 2921.92[msec]
fitness: 0.213937
--- pclomp::NDT (KDTREE, 1 threads) ---
single : 207.697[msec]
10times: 2059.19[msec]
fitness: 0.213937
--- pclomp::NDT (DIRECT7, 1 threads) ---
single : 139.433[msec]
10times: 1356.79[msec]
fitness: 0.214205
--- pclomp::NDT (DIRECT1, 1 threads) ---
single : 34.6418[msec]
10times: 317.03[msec]
fitness: 0.208511
--- pclomp::NDT (KDTREE, 8 threads) ---
single : 54.9903[msec]
10times: 500.51[msec]
fitness: 0.213937
--- pclomp::NDT (DIRECT7, 8 threads) ---
single : 63.1442[msec]
10times: 343.336[msec]
fitness: 0.214205
--- pclomp::NDT (DIRECT1, 8 threads) ---
single : 17.2353[msec]
10times: 100.025[msec]
fitness: 0.208511
Several methods for neighbor voxel search are implemented. If you select pclomp::KDTREE, results will be completely same as the original pcl::NDT. We recommend to use pclomp::DIRECT7 which is faster and stable. If you need extremely fast registration, choose pclomp::DIRECT1, but it might be a bit unstable.
Red: target, Green: source, Blue: aligned
Related packages
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].