Title :
A modeling technique for the recognition and attitude estimation of 3-D objects
Author :
Cao, Jun ; Mao, Yimin ; He, Zhenya
Author_Institution :
Dept. of Radio Eng., Southeast Univ., Nanjing, China
Abstract :
A novel method for rapid identification and 3-D attitude determination of polyhedral objects is presented. A least set of 2-D projections called the distinct view set is used to represent the 3-D object. For each distinct view, a shape descriptor with multiple levels of abstraction is used, making the method robust when the input image is noisy
Keywords :
abstract data types; identification; object recognition; solid modelling; 2-D projections; 3-D attitude determination; distinct view set; identification; modeling; multiple levels of abstraction; polyhedral objects; recognition; shape descriptor; Artificial intelligence; Computer vision; Helium; Image recognition; Layout; Multi-stage noise shaping; Noise level; Object recognition; Robustness; Shape;
Conference_Titel :
Communications, Computers and Signal Processing, 1993., IEEE Pacific Rim Conference on
Conference_Location :
Victoria, BC
Print_ISBN :
0-7803-0971-5
DOI :
10.1109/PACRIM.1993.407281
