projectLidarPointsOnImage

Project lidar point cloud data onto image coordinate frame

Syntax

imPts = projectLidarPointsOnImage(ptCloudIn,intrinsics,tform)

imPts = projectLidarPointsOnImage(worldPoints,intrinsics,tform)

[imPts,indices] = projectLidarPointsOnImage(___)

[___] = projectLidarPointsOnImage(___,Name,Value)

Description

imPts = projectLidarPointsOnImage(ptCloudIn,intrinsics,tform) projects lidar point cloud data onto an image coordinate frame using a rigid transformation between the lidar sensor and camera, tform, and a set of camera intrinsic parameters, intrinsics. The output imPts contains the 2-D coordinates of the projected points in the image frame.

imPts = projectLidarPointsOnImage(worldPoints,intrinsics,tform) projects lidar points, specified as 3-D coordinates in the world frame, onto image coordinate frame.

[imPts,indices] = projectLidarPointsOnImage(___) returns the linear indices of the projected points in the point cloud using any combination of input arguments in previous syntaxes.

[___] = projectLidarPointsOnImage(___,Name,Value) specifies options using one or more name-value arguments in addition to any combination of arguments in previous syntaxes. For example, 'ImageSize',[250 400] sets the size of the image on which to project the points to 250-by-400 pixels.

Examples

Overlay Projected Lidar Points on Image

Load ground truth data from a MAT file into the workspace. Extract the image and point cloud data from the ground truth data.

dataPath = fullfile(toolboxdir('lidar'),'lidardata','lcc','sampleColoredPtCloud.mat');
gt  = load(dataPath);
img = gt.im;
pc = gt.ptCloud;

Extract the camera intrinsic parameters from the ground truth data.

intrinsics = gt.camParams;

Extract the camera to lidar transformation matrix from the ground truth data, and invert to find the lidar to camera transformation matrix.

tform = invert(gt.tform);

Downsample the point cloud data.

p1 = pcdownsample(pc,'gridAverage',0.5);

Project the point cloud onto the image frame.

imPts = projectLidarPointsOnImage(p1,intrinsics,tform);

Overlay the projected points on the image.

figure
imshow(img)
hold on
plot(imPts(:,1),imPts(:,2),'.','Color','r')
hold off

Input Arguments

ptCloudIn — Point cloud

pointCloud object

Point cloud, specified as a pointCloud object.

worldPoints — Points in world coordinate frame

M-by-3 matrix | M-by-N-by-3 array

Points in the world coordinate frame, specified as an M-by-3 matrix or M-by-N-by-3 array. If you specify an M-by-3 matrix, each row contains 3-D world coordinates of a point in an unorganized point cloud that contains M points in total. If you specify an M-by-N-by-3 array, M and N represent the number of rows and columns, respectively, in an organized point cloud. Each channel of the array contains the 3-D world coordinates of that point.

Data Types: single | double

intrinsics — Camera intrinsic parameters

cameraIntrinsics object

Camera intrinsic parameters, specified as a cameraIntrinsics object.

tform — Lidar to camera rigid transformation

rigidtform3d object

Lidar to camera rigid transformation, specified as a rigidtform3d object.

Name-Value Arguments

Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Example: ImageSize=[250 400] sets the size of the image on which to project the points to 250-by-400 pixels.

Before R2021a, use commas to separate each name and value, and enclose Name in quotes.

Example: 'ImageSize',[250 400] sets the size of the image on which to project the points to 250-by-400 pixels.

Indices — Indices selected for projection onto image coordinate frame

vector of positive integers

Indices selected for projection onto image coordinate frame, specified as a vector of positive integers.

Data Types: single | double

ImageSize — Size of image on which points are projected

intrinsics.ImageSize (default) | two-element row vector

Size of the image on which the points are projected, specified as a two-element row vector of the form [width height] in pixels. The function uses the specified dimensions to filter out the projected points that are not in the field of view of the camera.

If you do no specify the 'ImageSize' argument, then the function uses the ImageSize property from the camera intrinsic parameters intrinsics to estimate the field of view of the camera.

Note

If you specify an 'ImageSize' argument greater than the default argument, then the function uses the default argument.

Data Types: single | double

Output Arguments

imPts — Points projected on image

M-by-2 matrix

Points projected on image, returned as an M-by-2 matrix. Each row contains the 2-D coordinates, in the form [x y], a point in the image frame.

Data Types: single | double

indices — Linear indices of projected points

vector of positive integers

Linear indices of the projected points of the point cloud, returned as a vector of positive integers.

Data Types: single | double

Extended Capabilities

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

Version History

Introduced in R2020b

R2022b: Supports rigidtform3d objects

You can now specify tform as a rigidtform3d object, which uses the premultiply convention. Although you can still specify tform as a rigid3d object, this object is not recommended because it uses the postmultiply convention. For more information, see Migrate Geometric Transformations to Premultiply Convention.