pcviewset

Manage data for point cloud based visual odometry and SLAM

Since R2020a

Description

The pcviewset object stores point cloud odometry and simultaneous localization and mapping (SLAM) data as a set of views and pairwise connections between views.

Creation

Syntax

vSet = pcviewset

Description

vSet = pcviewset creates a pcviewset object with default property names. Use object functions to perform actions such as adding, modifying, or removing views or connections.

Properties

Views — View attributes

empty three-column table (default) | three-column table

This property is read-only.

View attributes, specified as a three-column table. The table contains columns as described in this table.

Column	Description
ViewID	View identifier, specified as an integer. View identifiers are unique to a specific view.
AbsolutePose	Absolute pose of the view, specified as a rigidtform3d object.
PointCloud	Point cloud, specified as a pointCloud object.

Connections — Pairwise connections between views

empty four-column table (default) | four-column table

This property is read-only.

Pairwise connections between views, specified as a four-column table. The table contains columns as described in this table. Each row corresponds to one connection.

Column	Description
ViewID1	View identifier for the first view, specified as a unique integer.
ViewID2	View identifier for the second view, specified as a unique integer.
RelativePose	Relative pose of the second view with respect to the first view, specified as a rigidtform3d object.
InformationMatrix	Information matrix, specified as a 6-by-6 matrix. The information matrix represents the uncertainty of the measurement error and is the inverse of the covariance matrix.

NumViews — Number of views

0 (default) | nonnegative integer

This property is read-only.

Number of views, specified as a nonnegative integer.

NumConnections — Number of connections

0 (default) | nonnegative integer

This property is read-only.

Number of connections, specified as a nonnegative integer.

Object Functions

addView	Add views to view set
updateView	Update view in view set
deleteView	Delete view from view set
hasView	Check if view is in view set
addConnection	Add connection between views in view set
updateConnection	Update connection between views in a view set
deleteConnection	Delete a connection between views in view set
hasConnection	Check if connection between two views is in view set
findView	Find views associated with view identifiers
findConnection	Find connections associated with view identifiers
connectedViews	Connected views in view set
poses	Absolute poses associated with views in view set
createPoseGraph	Create pose graph
optimizePoses	Optimize absolute poses using relative pose constraints
plot	Plot point cloud view set views and connections

Examples

Perform Lidar Odometry Using Point Cloud Registration

Create a view set to hold odometry.

 vSet = pcviewset;

Create a Velodyne reader to read point clouds.

veloReader = velodyneFileReader('lidarData_ConstructionRoad.pcap','HDL32E');
ptCloud = readFrame(veloReader);

Preprocess one frame to remove the ground plane and to downsample point cloud.

elevationDelta = 25;
gridStep = 0.2;
groundPtsIdx = segmentGroundFromLidarData(ptCloud, ...
    ElevationAngleDelta=elevationDelta);
ptCloud = select(ptCloud,~groundPtsIdx,Output='full');
ptCloud = pcdownsample(ptCloud,'gridAverage',gridStep);

Initialize attributes for the first view.

absPose = rigidtform3d;
relPose = rigidtform3d;

Add the first view to the point cloud view set.

vSet = addView(vSet,1,absPose,PointCloud=ptCloud);

Initialize a point cloud map using the first view.

ptCloudMap = copy(ptCloud);

skipFrames = 5;
prevViewId = 1;
prevPtCloud = ptCloud;

Loop over frames to update odometry and the point cloud map.

for viewId = 6:skipFrames:40
    % Read point cloud.
    ptCloud = readFrame(veloReader,viewId);

    % Preprocess the frame.
    groundPtsIdx = segmentGroundFromLidarData(ptCloud, ...
        ElevationAngleDelta=elevationDelta);
    ptCloud = select(ptCloud,~groundPtsIdx,Output='full');
    ptCloud = pcdownsample(ptCloud,'gridAverage',gridStep);

    % Register new point cloud against the previous one.
    regGridStep = 5;
    relPose = pcregisterndt(ptCloud,prevPtCloud,regGridStep, ...
        InitialTransform=relPose);

    % Update the absolute pose.
    absPose = rigidtform3d(absPose.A * relPose.A);

    % Add new view and connection to the previous view.
    vSet = addView(vSet,viewId,absPose,PointCloud=ptCloud);
    vSet = addConnection(vSet,prevViewId,viewId,relPose);

    prevPtCloud = ptCloud;
    prevViewId = viewId;
end

Display the view set in a default 2-D view.

plot(vSet,ShowViewIds='on')
view(2)

Extended Capabilities

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

Version History

Introduced in R2020a

R2022b: Supports premultiply geometric transformation convention

Starting in R2022b, most Computer Vision Toolbox™ functions create and perform geometric transformations using the premultiply convention. Accordingly, the pcviewset object and its object functions are updated to use rigidtform3d objects, which support the premultiply convention. The pcviewset object now:

• Returns the Views property with the AbsolutePose column as a rigidtform3d object

• Returns the Connections property with the RelativePose column as a rigidtform3d object

Before, the properties returned AbsolutePose and RelativePose as rigid3d objects, which use the postmultiply convention.

For more information, see Migrate Geometric Transformations to Premultiply Convention.