2002 · 80 citations · 5 references
ComputingComputer ScienceComputational GeometryComputer VisionMachine VisionImage RegistrationMotion AnalysisMotion EstimationObject DetectionStereo VisionVisual TrackingCorrespondence MatchingCorrespondence ProblemFeature MatchingImage MatchingPoint TrackingStereo CorrespondenceStereo MatchingVisual Object Tracking
We present a simple yet powerful method to perform point-to-point matching between two images. The method uses an evidence measure, whose value for a given displacement reflects both the similarity between two locations and the confidence in a correct match. The measure is based on the gradient fields of the images, and can be computed quickly and in parallel. Accumulating the evidence measure for different displacements allows (1) stable computation, of correspondences without smoothing across motion boundaries, and (2) detection of dominant motions. The method works well both on highly textured images and on images containing regions of uniform intensities, and can be used for a variety of applications, including stereo, motion, and object tracking.
5
Berthold K. P. Horn, Brian G. Schunck · Artificial Intelligence · 1981 · 9.9K citations · Full text
Detection of binocular disparities
K. Prazdny · Biological Cybernetics · 1985 · 254 citations
Real-time binocular smooth pursuit
David Coombs, Christopher M. Brown · International Journal of Computer Vision · 1993 · 112 citations