|
eCommons@Cornell >
College of Engineering >
Computer Science >
Computer Science Technical Reports >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1813/6225
| Title: | A Gradient-Based Evidence Measure for Image Matching |
| Authors: | Scharstein, Daniel |
| Keywords: | computer science
technical report |
| Issue Date: | Aug-1994 |
| Publisher: | Cornell University |
| Citation: | http://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cs/TR94-1439 |
| Abstract: | We present a simple yet powerful method to perform point-to-point matching between two images. The method uses an \it{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, which can serve as attention cues in active vision systems. 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 vision, motion segmentation, and object tracking. |
| URI: | http://hdl.handle.net/1813/6225 |
| Appears in Collections: | Computer Science Technical Reports
|
Items in eCommons are protected by copyright, with all rights reserved, unless otherwise indicated.
|
