Title :
Geometry-based automatic object localization and 3-D pose detection
Author :
Magnor, Marcus A.
Author_Institution :
Comput. Graphics Lab., Stanford Univ., CA, USA
Abstract :
Given the image of a real-world scene and a polygonal 3D model of a depicted object, its apparent size, image coordinates, and 3D orientation are autonomously detected. Based on matching silhouette outline to edges in the image, an extensive search in parameter space converges to the best-matching set of parameter values. Apparent object size may a-priori be unknown, and no initial search parameter values need to be provided. Due to its high degree of parallelism, the algorithm is well suited for implementation on graphics hardware to achieve fast object recognition and 3D pose estimation
Keywords :
computational geometry; edge detection; feature extraction; image matching; object recognition; parallel algorithms; 3D orientation; 3D pose detection; 3D pose estimation; apparent object size; automatic object localization; best-matching set; edge matching; geometry-based object localization; graphics hardware; image coordinates; object recognition; parallel algorithm; parameter space search; polygonal 3D model; real-world scene; silhouette outline matching; Convolution; Detectors; Geometry; Image edge detection; Layout; Object detection; Pixel; Rendering (computer graphics); Solid modeling;
Conference_Titel :
Image Analysis and Interpretation, 2002. Proceedings. Fifth IEEE Southwest Symposium on
Conference_Location :
Sante Fe, NM
Print_ISBN :
0-7695-1537-1
DOI :
10.1109/IAI.2002.999907
