poses

Absolute poses associated with views in view set

Syntax

sensorPoses = poses(vSet)

Description

sensorPoses = poses(vSet) returns a table of absolute poses associated with the views contained in the view set, vSet.

Examples

Retrieve Absolute Poses from Image View Set

Load images into the workspace.

imageDir = fullfile(toolboxdir("vision"),"visiondata","structureFromMotion");
images = imageDatastore(imageDir);

Compute features for the first image.

I = im2gray(readimage(images,1));
pointsPrev = detectSURFFeatures(I);
[featuresPrev,pointsPrev] = extractFeatures(I,pointsPrev);

Create an image view set and add the extracted feature points to the image view set.

vSet = imageviewset;
vSet = addView(vSet,1,Points=pointsPrev);

Compute features and matches for the rest of the images.

for i = 2:numel(images.Files)
 I = im2gray(readimage(images,i));
 points = detectSURFFeatures(I);
 [features,points] = extractFeatures(I,points);
 vSet = addView(vSet,i,Features=features,Points=points);
 pairsIdx = matchFeatures(featuresPrev,features);
 vSet = addConnection(vSet,i-1,i,Matches=pairsIdx);
 featuresPrev = features;
end

Get the absolute poses.

sensorPoses = poses(vSet)

sensorPoses=5×2 table
    ViewId      AbsolutePose  
    ______    ________________

      1       1×1 rigidtform3d
      2       1×1 rigidtform3d
      3       1×1 rigidtform3d
      4       1×1 rigidtform3d
      5       1×1 rigidtform3d

Input Arguments

vSet — Image view set

imageviewset object

Image view set, specified as an imageviewset object.

Output Arguments

sensorPoses — Absolute poses

two-column table

Absolute poses, returned as a two-column table. The table contains columns as described in this table.

Column	Description
ViewID	View identifier, returned as a positive integer. View identifiers are unique to a specific view.
AbsolutePose	Absolute pose of the view, returned as a rigidtform3d or se3 object.

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

When generating code, the output argument sensorPoses is returned as a structure with fields ViewID and AbsolutePose.

Use posesSe3 instead of poses for code generation if you're using se3 poses as input to vset

GPU Code Generation
Generate CUDA® code for NVIDIA® GPUs using GPU 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 poses function now returns the AbsolutePose value in the sensorPoses argument as a rigidtform3d object, which uses the premultiply convention. Before, the function returned AbsolutePose as a rigid3d object, which uses the postmultiply convention. For more information, see Migrate Geometric Transformations to Premultiply Convention.