Main Content


Check if new key frame added in RGB-D visual SLAM object

Since R2024a



    hasAdded = hasNewKeyFrame(vslam) returns a logical value that indicates if a new key frame has been added within the RGB-D visual simultaneous localization and mapping (vSLAM) object vslam.


    collapse all

    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 = ""; 
    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  
        disp("Downloading fr3_office.tgz (1.38 GB). This download can take a few minutes.") 
        % Extract contents of the downloaded file
        disp("Extracting fr3_office.tgz (1.38 GB) ...") 

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

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

    while ~isDone(vslam)

    Input Arguments

    collapse all

    RGB-D visual SLAM object, specified as an rgbdvslam object.

    Output Arguments

    collapse all

    New key frame status, returned as a logical 0 (false) or 1 (true). A value of true indicates that a new key frame has been added within the RGB-D visual SLAM object vslam. A value of false indicates that no new key frame has been added. The object considers an image frame to be a key frame if the number of tracked feature points in the current frame satisfies one these conditions:

    • The number of tracked feature points is within the limits specified by the TrackFeatureRange property of the rgbdvslam object vslam.

    • The number of tracked feature points is greater than the upper limit specified by the TrackFeatureRange property of the rgbdvslam object vslam, and the number of skipped frames since adding the last key frame equals the value of the SkipMaxFrames property of vslam.

    The hasNewKeyFrame object function returns true only when the rgbdvslam object has added one or more new key frames since the last hasNewKeyFrame call. For example, if the rgbdvslam object adds only one key frame, then two consecutive calls to hasNewKeyFrame return true and false, respectively.

    Version History

    Introduced in R2024a

    See Also