Design of a 3-D vision system based on geometric knowledge

Hiroshi Dohi, Mitsuru Ishizuka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A design of a three-dimensional (3-D) vision system based on geometric knowledge is described. The advantage of this model-based approach is to provide a precise understanding and strong robustness against partial occlusions for the object represented by a geometric solid model. The main reason for difficulty in recognizing partially occluded objects is that there is no object model with every variety of partial occlusion. It is a problem to obtain a customized object representation in three-dimensional space. The proposed system can synthesize various images dynamically from the geometric model description by handling the solid modeler. The depth information is extracted from a single view with geometric knowledge. The configuration of the target object is treated as a hypothesis. The generate-and-test strategy is used for hypothesis verification.

Original languageEnglish
Title of host publicationProc Int Workshop Ind Appl Machine Intell Vision
Editors Anon
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages217-222
Number of pages6
Publication statusPublished - 1989
Externally publishedYes
EventProceedings of the International Workshop on Industrial Applications of Machine Intelligence and Vision - Tokyo, Japan
Duration: 1989 Apr 101989 Apr 12

Other

OtherProceedings of the International Workshop on Industrial Applications of Machine Intelligence and Vision
CityTokyo, Japan
Period89/4/1089/4/12

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Dohi, H., & Ishizuka, M. (1989). Design of a 3-D vision system based on geometric knowledge. In Anon (Ed.), Proc Int Workshop Ind Appl Machine Intell Vision (pp. 217-222). Publ by IEEE.