This example shows how to automatically detect and track a face in a live video stream, using the KLT algorithm.
Object detection and tracking are important in many computer vision applications including activity recognition, automotive safety, and surveillance. In this example you will develop a simple system for tracking a single face in a live video stream captured by a webcam. MATLAB provides webcam support through a Hardware Support Package, which you will need to download and install in order to run this example. The support package is available via the Support Package Installer.
The face tracking system in this example can be in one of two modes: detection or tracking. In the detection mode you can use a
vision.CascadeObjectDetector object to detect a face in the current frame. If a face is detected, then you must detect corner points on the face, initialize a
vision.PointTracker object, and then switch to the tracking mode.
In the tracking mode, you must track the points using the point tracker. As you track the points, some of them will be lost because of occlusion. If the number of points being tracked falls below a threshold, that means that the face is no longer being tracked. You must then switch back to the detection mode to try to re-acquire the face.
Create objects for detecting faces, tracking points, acquiring and displaying video frames.
% Create the face detector object. faceDetector = vision.CascadeObjectDetector(); % Create the point tracker object. pointTracker = vision.PointTracker('MaxBidirectionalError', 2); % Create the webcam object. cam = webcam(); % Capture one frame to get its size. videoFrame = snapshot(cam); frameSize = size(videoFrame); % Create the video player object. videoPlayer = vision.VideoPlayer('Position', [100 100 [frameSize(2), frameSize(1)]+30]);
Capture and process video frames from the webcam in a loop to detect and track a face. The loop will run for 400 frames or until the video player window is closed.
runLoop = true; numPts = 0; frameCount = 0; while runLoop && frameCount < 400 % Get the next frame. videoFrame = snapshot(cam); videoFrameGray = rgb2gray(videoFrame); frameCount = frameCount + 1; if numPts < 10 % Detection mode. bbox = faceDetector.step(videoFrameGray); if ~isempty(bbox) % Find corner points inside the detected region. points = detectMinEigenFeatures(videoFrameGray, 'ROI', bbox(1, :)); % Re-initialize the point tracker. xyPoints = points.Location; numPts = size(xyPoints,1); release(pointTracker); initialize(pointTracker, xyPoints, videoFrameGray); % Save a copy of the points. oldPoints = xyPoints; % Convert the rectangle represented as [x, y, w, h] into an % M-by-2 matrix of [x,y] coordinates of the four corners. This % is needed to be able to transform the bounding box to display % the orientation of the face. bboxPoints = bbox2points(bbox(1, :)); % Convert the box corners into the [x1 y1 x2 y2 x3 y3 x4 y4] % format required by insertShape. bboxPolygon = reshape(bboxPoints', 1, ); % Display a bounding box around the detected face. videoFrame = insertShape(videoFrame, 'Polygon', bboxPolygon, 'LineWidth', 3); % Display detected corners. videoFrame = insertMarker(videoFrame, xyPoints, '+', 'Color', 'white'); end else % Tracking mode. [xyPoints, isFound] = step(pointTracker, videoFrameGray); visiblePoints = xyPoints(isFound, :); oldInliers = oldPoints(isFound, :); numPts = size(visiblePoints, 1); if numPts >= 10 % Estimate the geometric transformation between the old points % and the new points. [xform, inlierIdx] = estimateGeometricTransform2D(... oldInliers, visiblePoints, 'similarity', 'MaxDistance', 4); oldInliers = oldInliers(inlierIdx, :); visiblePoints = visiblePoints(inlierIdx, :); % Apply the transformation to the bounding box. bboxPoints = transformPointsForward(xform, bboxPoints); % Convert the box corners into the [x1 y1 x2 y2 x3 y3 x4 y4] % format required by insertShape. bboxPolygon = reshape(bboxPoints', 1, ); % Display a bounding box around the face being tracked. videoFrame = insertShape(videoFrame, 'Polygon', bboxPolygon, 'LineWidth', 3); % Display tracked points. videoFrame = insertMarker(videoFrame, visiblePoints, '+', 'Color', 'white'); % Reset the points. oldPoints = visiblePoints; setPoints(pointTracker, oldPoints); end end % Display the annotated video frame using the video player object. step(videoPlayer, videoFrame); % Check whether the video player window has been closed. runLoop = isOpen(videoPlayer); end % Clean up. clear cam; release(videoPlayer); release(pointTracker); release(faceDetector);
Viola, Paul A. and Jones, Michael J. "Rapid Object Detection using a Boosted Cascade of Simple Features", IEEE CVPR, 2001.
Bruce D. Lucas and Takeo Kanade. An Iterative Image Registration Technique with an Application to Stereo Vision. International Joint Conference on Artificial Intelligence, 1981.
Carlo Tomasi and Takeo Kanade. Detection and Tracking of Point Features. Carnegie Mellon University Technical Report CMU-CS-91-132, 1991.
Jianbo Shi and Carlo Tomasi. Good Features to Track. IEEE Conference on Computer Vision and Pattern Recognition, 1994.
Zdenek Kalal, Krystian Mikolajczyk and Jiri Matas. Forward-Backward Error: Automatic Detection of Tracking Failures. International Conference on Pattern Recognition, 2010