Journal of the Korean Society for Precision Engineering (한국정밀공학회지)
- Volume 10 Issue 4
- /
- Pages.170-179
- /
- 1993
- /
- 1225-9071(pISSN)
- /
- 2287-8769(eISSN)
A study on correspondence problem of stereo vision system using self-organized neural network
Abstract
In this study, self-organized neural network is used to solve the vorrespondence problem of the axial stereo image. Edge points are extracted from a pair of stereo images and then the edge points of rear image are assined to the output nodes of neural network. In the matching process, the two input nodes of neural networks are supplied with the coordi- nates of the edge point selected randomly from the front image. This input data activate optimal output node and its neighbor nodes whose coordinates are thought to be correspondence point for the present input data, and then their weights are allowed to updated. After several iterations of updating, the weights whose coordinates represent rear edge point are converged to the coordinates of the correspondence points in the front image. Because of the feature map properties of self-organized neural network, noise-free and smoothed depth data can be achieved.
Keywords
- Stereo Vision;
- Correspondence Problem;
- Self-Organized Neural Network;
- Edge Detecion;
- 3D Data Extraction
- 스테레오 비젼;
- 대응문제;
- 자기조직 신경회로망;
- 에지추출;
- 3차원 정보추출;