Accession Number : ADA322738

Title :   Invariant and Calibration-Free Methods in Scene Reconstruction and Object Recognition.

Descriptive Note : Final rept.,

Corporate Author : GE CORPORATE RESEARCH AND DEVELOPMENT SCHENECTADY NY

Personal Author(s) : Hartley, Richard I. ; Mundy, Joseph L.

PDF Url : ADA322738

Report Date : 28 FEB 1997

Pagination or Media Count : 266

Abstract : This is the final technical report for a DARPA project (#MDA 972-91-C-0053) on object recognition through the use of Geometric Invariants. It gives an extended account of the work that was done at GE-CRD and by certain collaborating researchers during the time of this project. The report considers the subjects of reconstruction of scenes from multiple views with a projective camera, and the recognition of objects from a single or multiple views. The key reconstruction result is that projective reconstruction is possible from a set of more than one image of a point set. Methods of reconstruction using the fundamental matrix (from two views) and the trifocal tensor (from three views) are explored, as also is the possibility of self calibration of a camera, and consequent Euclidean reconstruction from three or more views. On the subject of object recognition from a single view, it is shown that by taking advantage of known, or hypothesized geometric structure of a scene being viewed, geometric invariants may be used for tasks of segmentation, grouping and object recognition.

Descriptors :   *IMAGE PROCESSING, *ARTIFICIAL INTELLIGENCE, DATA BASES, ALGORITHMS, DATA MANAGEMENT, MATRICES(MATHEMATICS), EIGENVALUES, THREE DIMENSIONAL, IMAGE INTENSIFICATION, PATTERN RECOGNITION, INVARIANCE, SET THEORY, MAPPING(TRANSFORMATIONS), PROJECTIVE GEOMETRY, POINT THEOREM, TRIANGULATION.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE