matlab-point-cloud-registration

Name: matlab-point-cloud-registration
Author: matlab

815stars105forks

How to install matlab-point-cloud-registration?

matlab/matlab-agentic-toolkit/matlab-point-cloud-registration

$npx -y skills add matlab/matlab-agentic-toolkit --skill matlab-point-cloud-registration

Installs into the current project.

Summary

Register 3-D point clouds using ICP, NDT, LOAM, FGR, phase correlation, and CPD algorithms. Use when registering or aligning 3-D point clouds, choosing a registration algorithm, tuning registration parameters, preprocessing point clouds for registration or combining point clouds

Files · 1

View on GitHub

SKILL.md

1	# Point Cloud Registration
2
3	Select `pcregistericp` with `Metric="planeToPlane"` as the starting point, evaluate algorithm accuracy using RMSE, and align the point clouds using `pcalign`.
4
5	## When to Use
6
7	- User asks to register, align or match 3-D point clouds represented as `pointCloud` objects
8	- User needs to choose or tune a registration algorithm
9	- User wants to build a map from multiple lidar scans
10	- User wants to combine or merge registered point clouds
11	- User asks about initial transformation estimation for registration
12	- User asks to preprocess point clouds before registration
13
14	## When NOT to Use
15
16	- User wants to register 2-D point clouds (use `matchScans`, `matchScansGrid`, or `matchScansLine`)
17	- User wants image registration (use `imregtform` or `imregcorr` from Image Processing Toolbox)
18
19	## Required Toolboxes
20
21	- Computer Vision Toolbox
22	- Lidar Toolbox
23
24	## Legacy Patterns to Avoid
25
26	\| Do NOT use \| Use instead \| Why \|
27	\|------------\|-------------\|-----\|
28	\| `rigid3d` for InitialTransform \| `rigidtform3d` \| `rigidtform3d` uses the premultiply transformation convention, which is more commonly used.\|
29
30	## Algorithm Selection Guide
31
32	### Local Registration
33
34	If you have an initial transformation or the point clouds are only slightly misaligned, try these local registration methods in this order. Use the RMSE output as the accuracy metric to minimize.
35
36	\| Algorithm \| Function \| Notes \|
37	\|-----------\|----------\|-------\|
38	\| Generalized ICP (plane-to-plane) \| `pcregistericp` with `Metric="planeToPlane"` \| Default starting point. Additionally, try `"planeToPlaneWithColor"` if the point cloud has color. \|
39	\| ICP (point-to-plane) \| `pcregistericp` with `Metric="pointToPlane"` \| Additionally, try `"pointToPlaneWithColor"` if the point cloud has color. \|
40	\| ICP (point-to-point) \| `pcregistericp` with `Metric="pointToPoint"` \| Simplest metric. Try if plane-based metrics are inaccurate. \|
41	\| LOAM \| `pcregisterloam` \| Requires organized point clouds. If the point cloud is not organized, but you have the lidar parameters available, use `pcorganize` to organize the point cloud. Use `detectLOAMFeatures` first to tune feature detection. It gives you more flexibility on the accuracy vs speed tradeoff since `detectLOAMFeatures` has parameters to control the number of features. \|
42	\| NDT \| `pcregisterndt` \| Tune the `gridStep` parameter for the scale of the scene. \|
43
44	### Ground Data Registration
45
46	If you don't have an initial transformation, but you know that the data corresponds to ground data, try phase correlation.
47
48	\| Algorithm \| Function \| Notes \|
49	\|-----------\|----------\|-------\|
50	\| Phase Correlation \| `pcregistercorr` \| Specifically designed for ground data. Not a local registration method. \|
51
52	### Global Registration
53
54	If there is no initial transformation and the point clouds are significantly misaligned (overlap less than 50%), first use a global registration approach to align the moving point cloud to the fixed point cloud, then optionally use a local registration method as a refinement step to improve accuracy. Note that global registration approaches are usually slower than local ones.
55
56	\| Algorithm \| Function \| Notes \|
57	\|-----------\|----------\|-------\|
58	\| FGR \| `pcregisterfgr` \| Feature-based approach. \|
59	\| CPD (rigid) \| `pcregistercpd` with `Transform="Rigid"` \| Probabilistic framework. It handles outliers well. Use for small point clouds. \|
60	\| CPD (nonrigid) \| `pcregistercpd` with `Transform="Nonrigid"` \| Only option for non-rigid/deformable registration. \|
61	\| FPFH feature matching \| `extractFPFHFeatures` + `pcmatchfeatures` + `estgeotform3d` \| Extract FPFH descriptors, match features, and estimate the transformation using the MSAC algorithm (a variant of RANSAC). Tune `NumNeighbors` in `extractFPFHFeatures` and `gridStep` in `pcdownsample` to ensure enough features and feature matches. \|
62
63	### General Guidelines
64
65	- The initial transformation is the transformation that aligns the moving point cloud to the fixed point cloud. It is important to set the `InitialTransform` name-value argument for local registration algorithms when an estimate is available. If registering a sequence of point clouds and no other estimate is available, assume constant speed and set the initial transformation to the transformation estimated between the previous pair of point clouds.
66	- The RMSE output of `pcregisterfgr` is not comparable to the RMSE output of the other registration functions because it is the root mean squared error between only inlier points. Use the Point Cloud Registration Analyzer app for comparable RMSE v

People who liked this also viewed

6 picks

Type

matlab-point-cloud-registration

815stars105forks

View on GitHub

How to install matlab-point-cloud-registration?

matlab/matlab-agentic-toolkit/matlab-point-cloud-registration

$npx -y skills add matlab/matlab-agentic-toolkit --skill matlab-point-cloud-registration

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Point Cloud Registration
2
3	Select `pcregistericp` with `Metric="planeToPlane"` as the starting point, evaluate algorithm accuracy using RMSE, and align the point clouds using `pcalign`.
4
5	## When to Use
6
7	- User asks to register, align or match 3-D point clouds represented as `pointCloud` objects
8	- User needs to choose or tune a registration algorithm
9	- User wants to build a map from multiple lidar scans
10	- User wants to combine or merge registered point clouds
11	- User asks about initial transformation estimation for registration
12	- User asks to preprocess point clouds before registration
13
14	## When NOT to Use
15
16	- User wants to register 2-D point clouds (use `matchScans`, `matchScansGrid`, or `matchScansLine`)
17	- User wants image registration (use `imregtform` or `imregcorr` from Image Processing Toolbox)
18
19	## Required Toolboxes
20
21	- Computer Vision Toolbox
22	- Lidar Toolbox
23
24	## Legacy Patterns to Avoid
25
26	\| Do NOT use \| Use instead \| Why \|
27	\|------------\|-------------\|-----\|
28	\| `rigid3d` for InitialTransform \| `rigidtform3d` \| `rigidtform3d` uses the premultiply transformation convention, which is more commonly used.\|
29
30	## Algorithm Selection Guide
31
32	### Local Registration
33
34	If you have an initial transformation or the point clouds are only slightly misaligned, try these local registration methods in this order. Use the RMSE output as the accuracy metric to minimize.
35
36	\| Algorithm \| Function \| Notes \|
37	\|-----------\|----------\|-------\|
38	\| Generalized ICP (plane-to-plane) \| `pcregistericp` with `Metric="planeToPlane"` \| Default starting point. Additionally, try `"planeToPlaneWithColor"` if the point cloud has color. \|
39	\| ICP (point-to-plane) \| `pcregistericp` with `Metric="pointToPlane"` \| Additionally, try `"pointToPlaneWithColor"` if the point cloud has color. \|
40	\| ICP (point-to-point) \| `pcregistericp` with `Metric="pointToPoint"` \| Simplest metric. Try if plane-based metrics are inaccurate. \|
41	\| LOAM \| `pcregisterloam` \| Requires organized point clouds. If the point cloud is not organized, but you have the lidar parameters available, use `pcorganize` to organize the point cloud. Use `detectLOAMFeatures` first to tune feature detection. It gives you more flexibility on the accuracy vs speed tradeoff since `detectLOAMFeatures` has parameters to control the number of features. \|
42	\| NDT \| `pcregisterndt` \| Tune the `gridStep` parameter for the scale of the scene. \|
43
44	### Ground Data Registration
45
46	If you don't have an initial transformation, but you know that the data corresponds to ground data, try phase correlation.
47
48	\| Algorithm \| Function \| Notes \|
49	\|-----------\|----------\|-------\|
50	\| Phase Correlation \| `pcregistercorr` \| Specifically designed for ground data. Not a local registration method. \|
51
52	### Global Registration
53
54	If there is no initial transformation and the point clouds are significantly misaligned (overlap less than 50%), first use a global registration approach to align the moving point cloud to the fixed point cloud, then optionally use a local registration method as a refinement step to improve accuracy. Note that global registration approaches are usually slower than local ones.
55
56	\| Algorithm \| Function \| Notes \|
57	\|-----------\|----------\|-------\|
58	\| FGR \| `pcregisterfgr` \| Feature-based approach. \|
59	\| CPD (rigid) \| `pcregistercpd` with `Transform="Rigid"` \| Probabilistic framework. It handles outliers well. Use for small point clouds. \|
60	\| CPD (nonrigid) \| `pcregistercpd` with `Transform="Nonrigid"` \| Only option for non-rigid/deformable registration. \|
61	\| FPFH feature matching \| `extractFPFHFeatures` + `pcmatchfeatures` + `estgeotform3d` \| Extract FPFH descriptors, match features, and estimate the transformation using the MSAC algorithm (a variant of RANSAC). Tune `NumNeighbors` in `extractFPFHFeatures` and `gridStep` in `pcdownsample` to ensure enough features and feature matches. \|
62
63	### General Guidelines
64
65	- The initial transformation is the transformation that aligns the moving point cloud to the fixed point cloud. It is important to set the `InitialTransform` name-value argument for local registration algorithms when an estimate is available. If registering a sequence of point clouds and no other estimate is available, assume constant speed and set the initial transformation to the transformation estimated between the previous pair of point clouds.
66	- The RMSE output of `pcregisterfgr` is not comparable to the RMSE output of the other registration functions because it is the root mean squared error between only inlier points. Use the Point Cloud Registration Analyzer app for comparable RMSE v

People who liked this also viewed

6 picks

Type