• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.9
• /
• pp.37-49
• /
• 1992

The standard definition of computational vision is a set of inverse problems of recovering surfaces from images. Thus the common characteristics of the most early vision problems are ill-posed. The main idea for solving ill-posed problems is to restrict the class of admissible solutions by introducing suitable a priori knowledge. Standard regurarization methods lead to satisfactory solutions of early vision problems but cannot deal effectively and directly with a few general problems, such as discontinuity and fusion of information from multiple modules. In this paper, we discuss limitations of standard regularization theory and present new stochastic method. We will outline a rigorous approach to overcome part of ill-posedness of image restoration, edge detection, and stereo vision problems, based on Bayes estimation and MRF(Markov random field) model, that effectively deals with the problems. This result makes one hope that this framework could be useful in the solution of other vision problems.

• IE interfaces
• /
• v.11 no.2
• /
• pp.93-106
• /
• 1998

This paper suggests a stereo vision-based algorithm for the 3-dimensional inspection of a crimped terminal. The crimped terminal is one of wire harness assemblies which transmit current or signals between a pair of electrical or electronic assemblies. Four types of nonconformities considered includes terminal rolling, band up/down, twist, and crimp height. To obtain stereo image correspondence, an algorithm using Hough transform is proposed. Coordinate transform is then applied to evaluate the degree of 3-dimensional nonconformities. The algorithm has been successfully tested on a number of real specimens collected from a wire harness factory. The test results show the feasibility of the proposed algorithm.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.1
• /
• pp.107-113
• /
• 2017

Unlike regular images, there is no ground truth for bio surface images. Result of biosurface imaging is not only significantly affected by the environment and the condition of the bio surface, it requires more detailed expression than regular images. Therefore, unlike algorithms tested on regular images, studies on bio surface images requires a highly precise optimization process. We aim to optimize the graph cut algorithm, known to be the most outstanding among the stereo visions, by considering baseline, lambda, and disparity range. Optimal results were in the range of 1~10 for lambda. The disparity ranged from -30 to -50, indicating an optimal value in a slightly higher range. Furthermore, we verified the tested optimization data using SIFT.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.29 no.11
• /
• pp.18-27
• /
• 2015

In this paper, we proposed the spinning right-angle stereo vision system to center the shifted object on 3-dimensional image using a human eyesight-like, and the system is reconstructed with conventional stereo vision system. In this proposed system, the centering results of objects on the 3-dimensional image are very good, and we got the parameter ratios 89~112% for the real measurement values. Therefore, the suggested the spinning right-angle stereo vision system have a high possibilities to be applied to many industrial system parts and to be used for robot system, automatic system, and etc.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06b
• /
• pp.227-230
• /
• 2010

비젼 기반의 휴먼 인체 추적 문제는 추정해야 할 파라미터의 수가 많고, 인체 구성 요소들 간의 가려짐등으로 인해 발생하는 포즈 간의 모호성 등으로 야기되는 어려움을 가지고 있다. 본 논문에서는 다양한 휴먼 상체 포즈에 따른 고차원 탐색 공간을 효율적으로 계산할 수 있는 Mean-Shift Belief Propagation (MSBP) 및 역기구학(Inverse Kinematics) 제약에 기반한 방법을 제안한다. 제안된 방법의 효율성을 증명하기 위해 실험을 기존에 제안된 방법들과의 비교 실험을 수행하였다.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.5
• /
• pp.83-83
• /
• 2004

The analysis of relative pose(position and rotation) between stereo cameras is very important to determine the solution that provides three-dimensional information for an arbitrary moving target with respect to robot-end. In the space of free camera-model, the rotational parameters act on non-linear factors acquiring a kinematical solution. In this paper the general solution of active stereo that gives a three-dimensional pose of moving object is presented. The focus is to achieve a derivation of linear equation between a robot′s end and active stereo cameras. The equation is consistently derived from the vector of quaternion space. The calibration of cameras is also derived in this space. Computer simulation and the results of error-sensitivity demonstrate the successful operation of the solution. The suggested solution can also be applied to the more complex real time tracking and quite general and are applicable in various stereo fields.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.5
• /
• pp.89-90
• /
• 2004

The analysis of relative pose(position and rotation) between stereo cameras is very important to determine the solution that provides three-dimensional information for an arbitrary moving target with respect to robot-end. In the space of free camera-model, the rotational parameters act on non-linear factors acquiring a kinematical solution. In this paper the general solution of active stereo that gives a three-dimensional pose of moving object is presented. The focus is to achieve a derivation of linear equation between a robot's end and active stereo cameras. The equation is consistently derived from the vector of quaternion space. The calibration of cameras is also derived in this space. Computer simulation and the results of error-sensitivity demonstrate the successful operation of the solution. The suggested solution can also be applied to the more complex real time tracking and quite general and are applicable in various stereo fields.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.593-595
• /
• 2019

원격지의 로봇을 조작함에 있어, 원격지의 상황을 정확히 인식하는 것이 우선적으로 필요하다. 본 연구에서는 로봇에 설치된 스테레오 카메라를 통해 입력된 비디오를 네트워크를 통해 전달하고, 조작 공간에 있는 사용자가 Head Mounted Display(HMD) 기기를 통해 원격지의 상황을 현장감 있게 파악할 수 있는 비전 시스템을 구현했다. 로봇 내 S/W의 효과적인 통합을 위해 카메라 입력 처리 및 비디오 스트리밍은 Ubuntu의 ROS를 이용하여 구현됐으며, 조작 공간의 HMD 기기 및 관련 조작 센서 통합은 Windows 상에 구현하여, 실험을 통해 원격지의 상황을 25fps 수준의 HD 해상도 비디오로 확인할 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.41-47
• /
• 2006

The range-based method is easy to get the 3D data in detail, but the image-based is not. In this paper. employing the magnifying lens. the new approach to get the 3D data in detail is suggested. The magnifying lens amplifies the disparity in stereo vision system and the amplification of disparity is to increase the resolution of the depth. We mathematically and experimentally verifies the fact to amplify the disparity and suggests the method to improve the original 3D data with the detail 3D data.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.170-179
• /
• 1993

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.