pcfitcuboid

Fit cuboid over point cloud

collapse all in page

Syntax

model = pcfitcuboid(ptCloudIn)
model = pcfitcuboid(ptCloudIn,indices)
model = pcfitcuboid(___,Name,Value)

Description

model = pcfitcuboid(ptCloudIn) fits a cuboid over the input point cloud data. The function stores the properties of the cuboid in the cuboidModel object, model.

example

model = pcfitcuboid(ptCloudIn,indices) fits a cuboid over a selected set of points, indices, in the input point cloud.

model = pcfitcuboid(___,Name,Value) specifies options using one or more name-value pair arguments in addition to any of the input argument combinations in previous syntaxes. For example, 'AzimuthRange,[-75 75]' sets the angular range for the azimuth angles of the function.

Examples

collapse all

Open Live Script

Fit bounding boxes around clusters in a point cloud.

Load the point cloud data into the workspace. 

data = load('drivingLidarPoints.mat');

Define and crop a region of interest (ROI) from the point cloud. Visualize the selected ROI of the point cloud.

roi = [-40 40 -6 9 -2 1];
in = findPointsInROI(data.ptCloud,roi);
ptCloudIn = select(data.ptCloud,in);
hcluster = figure;
panel = uipanel('Parent',hcluster,'BackgroundColor',[0 0 0]);
ax = axes('Parent',panel,'Color',[0 0 0]); 
pcshow(ptCloudIn,'MarkerSize',30,'Parent',ax)
title('Input Point Cloud')

Segment the ground plane. Visualize the segmented ground plane.

maxDistance = 0.3;
referenceVector = [0 0 1];
[~,inliers,outliers] = pcfitplane(ptCloudIn,maxDistance,referenceVector);
ptCloudWithoutGround = select(ptCloudIn,outliers,'OutputSize','full');
hSegment = figure;
panel = uipanel('Parent',hSegment,'BackgroundColor',[0 0 0]);
ax = axes('Parent',panel,'Color',[0 0 0]); 
pcshowpair(ptCloudIn,ptCloudWithoutGround,'Parent',ax)
legend('Ground Region','Non-Ground Region','TextColor', [1 1 1])
title('Segmented Ground Plane')

Segment the non-ground region of the point cloud into clusters. Visualize the segmented point cloud.

distThreshold = 1;
[labels,numClusters] = pcsegdist(ptCloudWithoutGround,distThreshold);
labelColorIndex = labels;
hCuboid = figure;
panel = uipanel('Parent',hCuboid,'BackgroundColor',[0 0 0]);
ax = axes('Parent',panel,'Color',[0 0 0]); 
pcshow(ptCloudIn.Location,labelColorIndex,'Parent',ax)
title('Fitting Bounding Boxes')
hold on

Fit bounding box on each cluster, visualized as orange highlights.

for i = 1:numClusters
    idx = find(labels == i);
    model = pcfitcuboid(ptCloudWithoutGround,idx);
    plot(model)
end

Input Arguments

collapse all

Point cloud, specified as a pointCloud object.

Indices of selected valid points, specified as a vector of positive integers.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

Name-Value Pair Arguments

Specify optional comma-separated pairs of Name,Value arguments. Name is the argument name and Value is the corresponding value. Name must appear inside quotes. You can specify several name and value pair arguments in any order as Name1,Value1,...,NameN,ValueN.

Example: 'AzimuthRange',[-75 75] sets the angular range for the azimuth angles of the function.

Range of azimuth angles over which to identify the orientation of the cuboid, specified as the comma-separated pair consisting of 'AzimuthRange' and a two-element row vector of real values in the range [0, 90].

Data Types: single | double

Step size of search window, specified as the comma-separated pair consisting of 'Resolution' and a positive scalar. The specified value must be less than or equal to the distance between the upper and lower bounds of the range of azimuth angles. For example, if the range of azimuth angles is [0, 90], the specified value must be less than or equal to 90.

Note

Decreasing the resolution will increase the computation time and memory footprint.

Data Types: single | double

Output Arguments

collapse all

Cuboid model, returned as a cuboidModel object.

References

[1] Xiao Zhang, Wenda Xu, Chiyu Dong and John M. Dolan, "Efficient L-Shape Fitting for Vehicle Detection Using Laser Scanners", IEEE  Intelligent Vehicles Symposium, June 2018

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

See Also

Functions

Objects

Introduced in R2020b

Lidar Toolbox Documentation

Support