plot

Plot 3-D map points and estimated camera trajectory in RGB-D visual SLAM

Since R2025a

Syntax

plot(vslam)

plot(vslam,Name=Value)

ax = plot(___)

Description

plot(vslam) plots the 3-D map points and estimated camera trajectory from the RGB-D visual SLAM object vslam.

plot(vslam,Name=Value) specifies options using one or more name-value arguments. For example, MarkerSize=10 sets the diameter of the marker size to 10 points.

ax = plot(___) returns the axes handle for the 3-D mapped points of the plot, using any combination of input arguments from previous syntaxes.

Examples

RGB-D Visual SLAM Using TUM RGB-D Data Set

Perform RGB-D visual simultaneous localization and mapping (vSLAM) using the data from the TUM RGB-D Benchmark. You can download the data to a temporary directory using a web browser or by running this code:

baseDownloadURL = "https://vision.in.tum.de/rgbd/dataset/freiburg3/rgbd_dataset_freiburg3_long_office_household.tgz"; 
dataFolder = fullfile(tempdir,"tum_rgbd_dataset",filesep); 
options = weboptions(Timeout=Inf);
tgzFileName = dataFolder+"fr3_office.tgz";
folderExists = exist(dataFolder,"dir");

% Create a folder in a temporary directory to save the downloaded file
if ~folderExists  
    mkdir(dataFolder) 
    disp("Downloading fr3_office.tgz (1.38 GB). This download can take a few minutes.") 
    websave(tgzFileName,baseDownloadURL,options); 
    
    % Extract contents of the downloaded file
    disp("Extracting fr3_office.tgz (1.38 GB) ...") 
    untar(tgzFileName,dataFolder); 
end

Create two imageDatastore objects. One to store the color images and the other to store the depth images.

colorImageFolder = dataFolder+"rgbd_dataset_freiburg3_long_office_household/rgb/";
depthImageFolder = dataFolder+"rgbd_dataset_freiburg3_long_office_household/depth/";

imdsColor = imageDatastore(colorImageFolder);
imdsDepth = imageDatastore(depthImageFolder);

Select the synchronized pair of color and depth images.

data = load("rgbDepthPairs.mat");
imdsColor=subset(imdsColor, data.indexPairs(:, 1));
imdsDepth=subset(imdsDepth, data.indexPairs(:, 2));

Specify your camera intrinsic parameters, and use them to create an RGB-D visual SLAM object.

intrinsics = cameraIntrinsics([535.4 539.2],[320.1 247.6],[480 640]);
depthScaleFactor = 5000;
vslam = rgbdvslam(intrinsics,depthScaleFactor);

Process each pair of color and depth images, and visualize the camera poses and 3-D map points.

for i = 1:numel(imdsColor.Files)
    colorImage = readimage(imdsColor,i);
    depthImage = readimage(imdsDepth,i);
    addFrame(vslam,colorImage,depthImage);

    if hasNewKeyFrame(vslam)
        % Query 3-D map points and camera poses
        xyzPoints = mapPoints(vslam);
        [camPoses,viewIds] = poses(vslam);

        % Display 3-D map points and camera trajectory
        plot(vslam);
    end

    % Get current status of system
    status = checkStatus(vslam);
    
    % Stop adding frames when tracking is lost
    if status == uint8(0)
        break
    end
end 

Once all the frames have been processed, reset the system.

while ~isDone(vslam)
    plot(vslam);
end

reset(vslam);

RGB-D Visual-Inertial SLAM Using OpenLORIS-Scene Data Set

Perform RGB-D visual-inertial SLAM using the data from the OpenLORIS-Scene Dataset. Download the data to a temporary directory using a web browser or by running this code:

dataFolder  = fullfile(tempdir,"OpenLORIS-Scene",filesep); 
downloadURL = "https://ssd.mathworks.com/supportfiles/shared_nav_vision/data/OpenLORIS-Scene_corridor1-4.zip";
zipFileName = dataFolder+"corridor1-4.zip";

if ~isfolder(dataFolder)
    mkdir(dataFolder);
    disp("Downloading corridor1-4.zip (1.13 GB). This download can take a few minutes.");
    options = weboptions('Timeout', Inf);
    websave(zipFileName, downloadURL, options); 
    unzip(zipFileName, dataFolder);
end

Create two imageDatastore objects. One to store the color images and the other to store the depth images.

imageFolder = fullfile(dataFolder,"OpenLORIS-Scene_corridor1-4");
imdsColor = imageDatastore(fullfile(imageFolder,"color"));
imdsDepth = imageDatastore(fullfile(imageFolder,"aligned_depth"));

Load the IMU measurements data and the camera-to-IMU transform.

data    = load("corridor4_IMU_data.mat");
gyro    = data.gyroDataCell;
accel   = data.accelDataCell;
cam2IMU = data.cam2IMU;

Specify the camera intrinsics, the IMU parameters, and use them to create an RGB-D visual-inertial SLAM object.

% Camera intrinsic and IMU parameters can be found in the downloaded  
% sensors.yaml file
intrinsics = cameraIntrinsics([6.1145098876953125e+02, 6.1148571777343750e+02],...
    [4.3320397949218750e+02, 2.4947302246093750e+02], [480, 848]);

imuParams = factorIMUParameters(AccelerometerBiasNoise=2.499999936844688e-05*eye(3),...
       AccelerometerNoise=0.00026780980988405645*eye(3),...
       GyroscopeNoise=1.0296060281689279e-05*eye(3),...
       GyroscopeBiasNoise=2.499999993688107e-07*eye(3),...
       SampleRate=250);

depthScaleFactor = 1000;
vslam = rgbdvslam(intrinsics, depthScaleFactor, imuParams, SkipMaxFrames=10,...
    CameraToIMUTransform=cam2IMU, TrackFeatureRange = [30, 150], DepthRange= [0.1, 6.5], ...
    NumPosesThreshold=20, MaxNumPoints=1.2e3);

Process image data and IMU data, and visualize the camera poses and 3-D map points.

for i = 1:numel(imdsColor.Files)
    colorImage  = readimage(imdsColor,i);
    depthImage  = readimage(imdsDepth,i);
    addFrame(vslam, colorImage, depthImage, gyro{i}, accel{i});

    if hasNewKeyFrame(vslam)
        plot(vslam);
    end
end

Once all the frames have been processed, reset the system.

while ~isDone(vslam)
    if hasNewKeyFrame(vslam)
        ax = plot(vslam);
    end
end
view(ax, 0, 90)

reset(vslam);

Input Arguments

vslam — RGB-D visual SLAM object

rgbdvslam object

RGB-D visual SLAM object, specified as an rgbdvslam 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: plot(vslam,MarkerSize=10), sets the diameter of the marker to 10 points.

MarkerSize — Diameter of markers for 3-D map points

6 (default) | positive integer

Diameter of the markers for the 3-D map points, specified as a positive integer in points.

MarkerColor — Color of markers for 3-D map points

[0 1 0] (default) | RGB triplet | short or long color name

Color of the markers for the 3-D map points, specified as an RGB triplet or a short or long color name. Each value within an RGB triplet must be in the range [0 1].

ColorSource — Colormap source for the markers

"Y" (default) | "X" | "Z" | "MarkerColor"

Colormap source for markers, specified as "X", "Y", "Z", or "MarkerColor".

CameraSize — Width of camera base

0.1 (default) | positive scalar

Width of the camera base, specified as a positive scalar in the data units of the axes.

CameraColor — Color of camera

[1 0 0] (default) | RGB triplet | short or long color name

Color of the camera, specified as an RGB triplet or a short or long color name. Each value within an RGB triplet must be in the range [0 1].

Parent — Axes for visualization

Axes object | UIAxes object

Axes for visualization, specified as an Axes graphics object or a UIAxes object. Use this name-value argument to visualize the plot in a UI for which you have specified Figure and Axes properties.

Output Arguments

ax — Axes handle

Axes graphics object

Axes handle, returned as an axes graphics object.

Version History

Introduced in R2025a