Title :
Class-based grouping in perspective images
Author :
Zisserman, Andrew ; Mundy, Joe ; Forsyth, David ; Liu, Jane ; Pillow, Nic ; Rothwell, Charlie ; Utcke, Sven
Author_Institution :
Dept. of Eng. Sci., Oxford Univ., UK
Abstract :
In any object recognition system a major and primary task is to associate those image features, within an image of a complex scene, that arise from an individual object. The key idea here is that a geometric class defined in 3D induces relationships in the image which must hold between points on the image outline (the perspective projection of the object). The resulting image constraints enable both identification and grouping of image features belonging to objects of that class. The classes include surfaces of revolution, canal surfaces (pipes) and polyhedra. Recognition proceeds by first recognising an object as belonging to one of the classes (for example a surface of revolution) and subsequently identifying the object (for example as a particular vase). This differs from conventional object recognition systems where recognition is generally targetted at particular objects. These classes also support the computation of 3D invariant descriptions including symmetry axes, canonical coordinate frames and projective signatures. The constraints and grouping methods are viewpoint invariant, and proceed with no information on object pose. We demonstrate the effectiveness of this class-based grouping on real, cluttered scenes using grouping algorithms developed for rotationally symmetric surfaces, canal-surfaces and polyhedra
Keywords :
computational geometry; feature extraction; image recognition; object recognition; 3D geometric class; 3D invariant descriptions; canal surfaces; canonical coordinate frames; class-based grouping; complex scene; feature grouping; feature identification; grouping algorithms; image constraints; image features; image outline; individual object; object recognition system; perspective images; perspective projection; polyhedra; projective signatures; real cluttered scenes; rotationally symmetric surfaces; symmetry axes; Face recognition; Feature extraction; Image edge detection; Image recognition; Irrigation; Layout; Libraries; Object recognition; Robot kinematics; Target recognition;
Conference_Titel :
Computer Vision, 1995. Proceedings., Fifth International Conference on
Conference_Location :
Cambridge, MA
Print_ISBN :
0-8186-7042-8
DOI :
10.1109/ICCV.1995.466788