Detect Multiple Planes from Point Cloud

Load the point cloud.

load('object3d.mat')

Display and label the point cloud.

figure
pcshow(ptCloud)
xlabel('X(m)')
ylabel('Y(m)')
zlabel('Z(m)')
title('Original Point Cloud')

Set the maximum point-to-plane distance (2cm) for plane fitting.

maxDistance = 0.02;

Set the normal vector of the plane.

referenceVector = [0,0,1];

Set the maximum angular distance to 5 degrees.

maxAngularDistance = 5;

Detect the first plane, the table, and extract it from the point cloud.

[model1,inlierIndices,outlierIndices] = pcfitplane(ptCloud,...
            maxDistance,referenceVector,maxAngularDistance);
plane1 = select(ptCloud,inlierIndices);
remainPtCloud = select(ptCloud,outlierIndices);

Set the region of interest to constrain the search for the second plane, left wall.

roi = [-inf,inf;0.4,inf;-inf,inf];
sampleIndices = findPointsInROI(remainPtCloud,roi);

Detect the left wall and extract it from the remaining point cloud.

[model2,inlierIndices,outlierIndices] = pcfitplane(remainPtCloud,...
            maxDistance,'SampleIndices',sampleIndices);
plane2 = select(remainPtCloud,inlierIndices);
remainPtCloud = select(remainPtCloud,outlierIndices);

Plot the two planes and the remaining points.

figure
pcshow(plane1)
title('First Plane')

figure
pcshow(plane2)
title('Second Plane')

figure
pcshow(remainPtCloud)
title('Remaining Point Cloud')