Representation, Acquisition and Utilization of World Model in Computer Vision
| Project/Area Number |
60302048
|
|---|
| Research Category |
Grant-in-Aid for Co-operative Research (A)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
計算機工学
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
TSUJI Saburo Faculty of Engineering Science, Osaka University, 基礎工学部, 教授 (60029527)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TORIWAKI Jun-ichiro Faculty of Engineering, Nagoya University, 工学部, 教授 (30023138)
MATSUYAMA Takashi Faculty of Engineering, Tohoku University, 工学部, 助教授 (10109035)
SUGIHARA Koukichi Faculty of Engineering, University of Tokyo, 工学部, 助教授 (40144117)
KITAHASHI Tadahira Institute of Industrial Science, Osaka University, 産業科学研究所, 教授 (70029453)
OHTA Yuichi Institute of Information Science and Electronics,Tsukuba University, 電子情報工学系, 講師 (50115804)
|
|---|
| Project Period (FY) |
1985 – 1986
|
| Project Status |
Completed (Fiscal Year 1986)
|
| Budget Amount *help |
¥1,500,000 (Direct Cost: ¥1,500,000)
Fiscal Year 1986: ¥1,500,000 (Direct Cost: ¥1,500,000)
|
|---|
| Keywords | Computer Vision / World Model / Computer Graphics / Knowledge / 3-D Model / 運動モデル |
|---|
| Research Abstract |
The central problem of computer vision is to represent the environments by world models. Various models have been proposed and studied, however any intensive research has not been made on comparison between these models. The objective of this cooperative research is to discuss on these models by authorities in computer vision and find the most promissing future direction of the research. Following models have been presented and compared.
1. Geometrical model
Effectiveness and efficiency of geometrical models used for computer vision and planning of robots are discussed. Their model structures developed for the computer graphics are not sufficient for the computer vision, and we need to develop new data structures.
2. Learning model
Methods for learning models from examples shown are presented, and the model strucutres needed for the machine vision are discussed.
3. Voxel model
Voxel models represented by 3-D data are presented. The computation using the models and applications for the computer graphics are discussed.
4. Structural line models
Representation of curved objects by structural lines and its mathematics are presented.
5 Map models
Map models which represent various data over wide areas are presented, and their structures and processing methods are discussed.
6. Overall discussions
Problems of these models, methods for utilizing them, and relations with the industrial vision are discussed to explore the directions of future researches.
|
Report
(1 results)
Research Products
(28 results)
