我正在尝试开发一个对象跟踪脚本，在每个时间点找到所有对象的质心，以便我可以根据每帧之间的时间计算它们的速度。我正在使用基于运动的多目标跟踪教程，并且已经能够成功地使用我的视频，但现在我想弄清楚如何提取每个对象的质心数据，然后计算速度！如果您有任何建议，请告诉我们。
最好，本
function multiObjectTracking()
% Create System objects used for reading video, detecting moving objects,
% and displaying the results.
obj = setupSystemObjects();
tracks = initializeTracks(); % Create an empty array of tracks.
nextId = 1; % ID of the next track
% Detect moving objects, and track them across video frames.
while ~isDone(obj.reader)
frame = readFrame();
[centroids, bboxes, mask] = detectObjects(frame);
predictNewLocationsOfTracks();
[assignments, unassignedTracks, unassignedDetections] = ...
detectionToTrackAssignment();
updateAssignedTracks();
updateUnassignedTracks();
deleteLostTracks();
createNewTracks();
displayTrackingResults();
end
function obj = setupSystemObjects()
% Initialize Video I/O
% Create objects for reading a video from a file, drawing the tracked
% objects in each frame, and playing the video.
% Create a video file reader.
obj.reader = vision.VideoFileReader('Beads.wmv');
% Create two video players, one to display the video,
% and one to display the foreground mask.
obj.videoPlayer = vision.VideoPlayer('Position', [20, 400, 700, 400]);
obj.maskPlayer = vision.VideoPlayer('Position', [740, 400, 700, 400]);
% Create System objects for foreground detection and blob analysis
% The foreground detector is used to segment moving objects from
% the background. It outputs a binary mask, where the pixel value
% of 1 corresponds to the foreground and the value of 0 corresponds
% to the background.
obj.detector = vision.ForegroundDetector('NumGaussians', 3, ...
'NumTrainingFrames', 40, 'MinimumBackgroundRatio', 0.7);
% Connected groups of foreground pixels are likely to correspond to moving
% objects. The blob analysis System object is used to find such groups
% (called 'blobs' or 'connected components'), and compute their
% characteristics, such as area, centroid, and the bounding box.
obj.blobAnalyser = vision.BlobAnalysis('BoundingBoxOutputPort', true, ...
'AreaOutputPort', true, 'CentroidOutputPort', true, ...
'MinimumBlobArea', 400);
end
function tracks = initializeTracks()
% create an empty array of tracks
tracks = struct(...
'id', {}, ...
'bbox', {}, ...
'kalmanFilter', {}, ...
'age', {}, ...
'totalVisibleCount', {}, ...
'consecutiveInvisibleCount', {});
end
function frame = readFrame()
frame = obj.reader.step();
end
function [centroids, bboxes, mask] = detectObjects(frame)
% Detect foreground.
mask = obj.detector.step(frame);
% Apply morphological operations to remove noise and fill in holes.
mask = imopen(mask, strel('rectangle', [3,3]));
mask = imclose(mask, strel('rectangle', [15, 15]));
mask = imfill(mask, 'holes');
% Perform blob analysis to find connected components.
[~, centroids, bboxes] = obj.blobAnalyser.step(mask);
end
function predictNewLocationsOfTracks()
for i = 1:length(tracks)
bbox = tracks(i).bbox;
% Predict the current location of the track.
predictedCentroid = predict(tracks(i).kalmanFilter);
% Shift the bounding box so that its center is at
% the predicted location.
predictedCentroid = int32(predictedCentroid) - bbox(3:4) / 2;
tracks(i).bbox = [predictedCentroid, bbox(3:4)];
end
end
function [assignments, unassignedTracks, unassignedDetections] = ...
detectionToTrackAssignment()
nTracks = length(tracks);
nDetections = size(centroids, 1);
% Compute the cost of assigning each detection to each track.
cost = zeros(nTracks, nDetections);
for i = 1:nTracks
cost(i, :) = distance(tracks(i).kalmanFilter, centroids);
end
% Solve the assignment problem.
costOfNonAssignment = 20;
[assignments, unassignedTracks, unassignedDetections] = ...
assignDetectionsToTracks(cost, costOfNonAssignment);
end
function updateAssignedTracks()
numAssignedTracks = size(assignments, 1);
for i = 1:numAssignedTracks
trackIdx = assignments(i, 1);
detectionIdx = assignments(i, 2);
centroid = centroids(detectionIdx, :);
bbox = bboxes(detectionIdx, :);
% Correct the estimate of the object's location
% using the new detection.
correct(tracks(trackIdx).kalmanFilter, centroid);
% Replace predicted bounding box with detected
% bounding box.
tracks(trackIdx).bbox = bbox;
% Update track's age.
tracks(trackIdx).age = tracks(trackIdx).age + 1;
% Update visibility.
tracks(trackIdx).totalVisibleCount = ...
tracks(trackIdx).totalVisibleCount + 1;
tracks(trackIdx).consecutiveInvisibleCount = 0;
end
end
function updateUnassignedTracks()
for i = 1:length(unassignedTracks)
ind = unassignedTracks(i);
tracks(ind).age = tracks(ind).age + 1;
tracks(ind).consecutiveInvisibleCount = ...
tracks(ind).consecutiveInvisibleCount + 1;
end
end
function deleteLostTracks()
if isempty(tracks)
return;
end
invisibleForTooLong = 20;
ageThreshold = 8;
% Compute the fraction of the track's age for which it was visible.
ages = [tracks(:).age];
totalVisibleCounts = [tracks(:).totalVisibleCount];
visibility = totalVisibleCounts ./ ages;
% Find the indices of 'lost' tracks.
lostInds = (ages < ageThreshold & visibility < 0.6) | ...
[tracks(:).consecutiveInvisibleCount] >= invisibleForTooLong;
% Delete lost tracks.
tracks = tracks(~lostInds);
end
function createNewTracks()
centroids = centroids(unassignedDetections, :);
bboxes = bboxes(unassignedDetections, :);
for i = 1:size(centroids, 1)
centroid = centroids(i,:);
bbox = bboxes(i, :);
% Create a Kalman filter object.
kalmanFilter = configureKalmanFilter('ConstantVelocity', ...
centroid, [200, 50], [100, 25], 100);
% Create a new track.
newTrack = struct(...
'id', nextId, ...
'bbox', bbox, ...
'kalmanFilter', kalmanFilter, ...
'age', 1, ...
'totalVisibleCount', 1, ...
'consecutiveInvisibleCount', 0);
% Add it to the array of tracks.
tracks(end + 1) = newTrack;
% Increment the next id.
nextId = nextId + 1;
end
end
function displayTrackingResults()
% Convert the frame and the mask to uint8 RGB.
frame = im2uint8(frame);
mask = uint8(repmat(mask, [1, 1, 3])) .* 255;
minVisibleCount = 8;
if ~isempty(tracks)
% Noisy detections tend to result in short-lived tracks.
% Only display tracks that have been visible for more than
% a minimum number of frames.
reliableTrackInds = ...
[tracks(:).totalVisibleCount] > minVisibleCount;
reliableTracks = tracks(reliableTrackInds);
% Display the objects. If an object has not been detected
% in this frame, display its predicted bounding box.
if ~isempty(reliableTracks)
% Get bounding boxes.
bboxes = cat(1, reliableTracks.bbox);
% Get ids.
ids = int32([reliableTracks(:).id]);
% Create labels for objects indicating the ones for
% which we display the predicted rather than the actual
% location.
labels = cellstr(int2str(ids'));
predictedTrackInds = ...
[reliableTracks(:).consecutiveInvisibleCount] > 0;
isPredicted = cell(size(labels));
isPredicted(predictedTrackInds) = {' predicted'};
labels = strcat(labels, isPredicted);
% Draw the objects on the frame.
frame = insertObjectAnnotation(frame, 'rectangle', ...
bboxes, labels);
% Draw the objects on the mask.
mask = insertObjectAnnotation(mask, 'rectangle', ...
bboxes, labels);
end
end
% Display the mask and the frame.
obj.maskPlayer.step(mask);
obj.videoPlayer.step(frame);
end
end
答案 0 :(得分：0)
由于每个帧中都有对象的质心，因此可以通过减去连续的质心来计算其速度（以像素/帧为单位）。