Tracking and Motion Estimation

Optical flow, activity recognition, motion estimation, and tracking

Start Here

Motion estimation and tracking are key activities in many computer vision applications including activity recognition, traffic monitoring, automotive safety, and surveillance.


configureKalmanFilter Create Kalman filter for object tracking
disparity Disparity map between stereo images
extractFeatures Extract interest point descriptors
extractHOGFeatures Extract histogram of oriented gradients (HOG) features
insertObjectAnnotation Annotate truecolor or grayscale image or video stream
assignDetectionsToTracks Assign detections to tracks for multiobject tracking
matchFeatures Find matching features


vision.KalmanFilter Kalman filter for object tracking

System Objects

vision.BlobAnalysis Properties of connected regions
vision.BlockMatcher Estimate motion between images or video frames
vision.ForegroundDetector Foreground detection using Gaussian mixture models
vision.HistogramBasedTracker Histogram-based object tracking
vision.OpticalFlow Estimate object velocities
vision.PointTracker Track points in video using Kanade-Lucas-Tomasi (KLT) algorithm
vision.TemplateMatcher Locate template in image


Blob Analysis Compute statistics for labeled regions
Block Matching Estimate motion between images or video frames
Block Processing Repeat user-specified operation on submatrices of input matrix
2-D Correlation Compute 2-D cross-correlation of two input matrices
Deinterlacing Remove motion artifacts by deinterlacing input video signal
Find Local Maxima Find local maxima in matrices
Optical Flow Estimate object velocities
Gaussian Pyramid Perform Gaussian pyramid decomposition
Template Matching Locate a template in an image
Was this topic helpful?