• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Experimental Research on Intelligent Image Segmentation System

Research Project

Project/Area Number 01850077
Research Category

Grant-in-Aid for Developmental Scientific Research

Allocation TypeSingle-year Grants
Research Field 計算機工学
Research InstitutionOsaka University

Principal Investigator

SHIRAI Yoshiaki  Osaka University, Faculty of Engineering, Professor, 工学部, 教授 (50206273)

Co-Investigator(Kenkyū-buntansha) ETOH Minoru  Matsushita Electric Industrial Co., Ltd., Researcher (CENTRAL RESEARCH LAB.), 中央研究所, 研究員
MIURA Jun  Osaka University, Faculty of Engineering, Research Associate, 工学部, 助手 (90219585)
ASADA Minoru  Osaka University, Faculty of Engineering, Associate Professor, 工学部, 助教授 (60151031)
川原 功  松下電器産業(株), 中央研究所, 研究員
Project Period (FY) 1990 – 1991
Project Status Completed (Fiscal Year 1991)
Budget Amount *help
¥13,900,000 (Direct Cost: ¥13,900,000)
Fiscal Year 1991: ¥5,100,000 (Direct Cost: ¥5,100,000)
Fiscal Year 1990: ¥2,900,000 (Direct Cost: ¥2,900,000)
Fiscal Year 1989: ¥5,900,000 (Direct Cost: ¥5,900,000)
KeywordsImage Processing / Segmentation / Stereo Vision / Image Understanding / Image Processor / Multi-Stage Processing / カラ-画像 / 領域分割 / 画像解釈 / 3次元特徴 / 高速化 / 特徴空間 / ヒストグラム分割 / 知識表現
Research Abstract

1 Rough Segmentation of Specified Object Region
We segmented a color image into several regions using color similarity, and used the result as an initial scene interpretation. We used the partial 3-D information derived from the initial segmentation to interpret the scene in details. The validity of our method was shown by applying it to several kinds of real scenes. Moreover, we developed a method of interpreting more complicated scenes using the depth information obtained by our stereo matching method.
2 Accurate Region Extraction from Rough Segmentation
We found that the existing methods were not applicable to objects like humans that consist of multiple parts such as faces and clothes. Then, we developed a method which detects an accurate boundary between a specified object and the background assuming it consists of several parts.
3 Design and Preliminary Implementation of High-Speed Processor for Image Segmentation
Conventional high-speed image processors are not sufficient for unage segmentation. Construction of 2-D histogram for initial color image segnientation and spatial convolution (2Ox2O) for feature extraction are major processing to speed up the image segmentation. A high-speed processors are constructed by adding these modules to a structure-variable image processor. We checked the effectiveness of the processing time by applying it to the image segmentation.

Report

(4 results)
  • 1991 Annual Research Report   Final Research Report Summary
  • 1990 Annual Research Report
  • 1989 Annual Research Report
  • Research Products

    (7 results)

All Other

All Publications (7 results)

  • [Publications] 白井 良明(第一著者): "Improvement of a Convetional AGV ーFlexible Path Selection and Obstacle Detectionー" Proc.Japan U.S.A.Symposium on Flexible Automation. 481-484 (1990)

    • Related Report
      1990 Annual Research Report
  • [Publications] 白井 良明: "Flexible Path Selection and Obstacle Avoidance for AGV (Invited Paper)" Proc.IEEE Int.Workshop on Intelligent Motion Contorol. IT39-IT44 (1990)

    • Related Report
      1990 Annual Research Report
  • [Publications] 浅田 稔(第一著者): "マルチセンサ情報を動的に統合することによる道路シ-ンの解釈とモデリング" 情報処理学会論文誌. 31. 12 (1990)

    • Related Report
      1990 Annual Research Report
  • [Publications] 西元善郎: "A feature-based stereo model using disparity histograms of multi-resolution channels" Advanced Robotics. 3-1. 17-33 (1989)

    • Related Report
      1989 Annual Research Report
  • [Publications] 白井良明: "Robot Vision-Range Data Acquisition and Utilization-" Proc.6th Scandinavian on Image Analysis. 15-23 (1989)

    • Related Report
      1989 Annual Research Report
  • [Publications] 浅田稔: "Building a world model for a mobile robot using dynamic semantic constraints" Proc.of 11th Int.Joint Conf on Artificial Intelligence. 1629-1634 (1989)

    • Related Report
      1989 Annual Research Report
  • [Publications] 浅田稔: "Interpretation and integration of height maps from a range image sequence" Proc.of IEEE/RSJ Int Workshop on Intelligent Robot and Systems. 54-61 (1989)

    • Related Report
      1989 Annual Research Report

URL: 

Published: 1989-04-01   Modified: 2019-02-15  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi