Neural-Network Model for Compensation of Lens Distortion in Camera Calibration

정병묵 한국정밀공학회 2018 International Journal of Precision Engineering and Vol.19 No.7

Camera calibration for machine vision is critical in three-dimensional (3-D) measurement systems based on a digital light processing (DLP) projector and a camera. The Z-height of the measurement point is calculated using the phase value observed by the camera when a fringe pattern is scanned from a projection onto an object. On the other hand, the X and Y coordinates are obtained from the camera coordinates using a transformation matrix, and the mathematical model for lens distortion is additionally used. However, the errors for x and y coordinates are 10 times larger than the z-height error in an experiment. This is because the lens distortion is not sufficiently compensated in the mathematical model considering only the position from the lens center. Therefore, the neural network (NN) model that considers the measurement distance in addition to the position is proposed in this paper. Experiments were conducted on a 100 × 100 mm2 area, and a maximum error of 0.5 mm is observed for the mathematical model. However, when the NN model considering the height of the object is used, the error is reduced by 60% to 0.2 mm.

Flexible Vision Inspection for Seat Frame of Automobile using Slit Beam

정병묵,소범식,이상훈 한국정밀공학회 2011 International Journal of Precision Engineering and Vol. No.

Today’s world automobile market is highly competitive. Quality of automobile is considered even more important and thus efforts are being made to improve the quality of automobile parts in order to survive in such competitive market. Despite rapid development of inspection devices using the vision system, there are few inspection systems for automobile parts. The reason is because the inspection with only one camera is nearly impossible, since automobile parts are three-dimensional and large. The seat frame, one of the typical automobile parts, has various models and is assembled using more than 20subparts. This paper suggests a flexible assembly inspection system of seat frame through the following procedures: first, the inspection method is standardized so that the system can cope with not only some currently existing models but also latent models in the future. Second, 6 cameras are used for inspecting seat frame assembly; 4 cameras are for measuring accuracy, and 2 for right and left-hand sides. Third, a simple pattern matching method is proposed for checking the position of assembly parts. Finally, slit beam method is proposed for checking the existence of assembly parts. Especially, it is very effective to inspect assembly of automobile parts with 3D shape and complex background image.

최적의 퍼지제어규칙을 얻기위한 퍼지학습법

정병묵,Chung, Byeong-Mook 대한기계학회 1996 大韓機械學會論文集A Vol.20 No.2

A fuzzy learning algorithm to get the optimal fuzzy rules is presented in this paper. The algorithm introduces a reference model to generate a desired output and a performance index funtion instead of the performance index table. The performance index funtion is a cost function based on the error and error-rate between the reference and plant output. The cost function is minimized by a gradient method and the control input is also updated. In this case, the control rules which generate the desired response can be obtained by changing the portion of the error-rate in the cost funtion. In SISO(Single-Input Single- Output)plant, only by the learning delay, it is possible to experss the plant model and to get the desired control rules. In the long run, this algorithm gives us the good control rules with a minimal amount of prior informaiton about the environment.

역진자 시스템에서 서로 다른 학습 지연을 사용한 퍼지학습법 ( Fuzzy Learning Control using Other Learning Delays in Inverted Pendulum System )

정병묵,임윤규 대한기계학회 1998 대한기계학회 춘추학술대회 Vol.- No.-

A Learning Method for Multivariable PID Control Synthesis Based on Estimated Plant Jacobian

정병묵,임윤규,Gregory D. Buckner 제어·로봇·시스템학회 2009 International Journal of Control, Automation, and Vol.7 No.5

Despite decades of research involving optimal control of multivariable systems, such controllers require accurate linear models of the plant dynamics. Real systems contain nonlinearities and high-order dynamics that may be difficult to model using conventional techniques. This paper presents a novel learning control (LC) method for PID controllers that doesn’t require explicit modeling of the plant dynamics. This method utilizes gradient descent techniques to iteratively reduce an error-related objective function. Simulations involving a hydrofoil catamaran show that the proposed PID-LC algorithm improves controller performance compared to LQR controllers derived from multivariable models.

자동 고속 분사기의 정밀 장력제어 시스템 개발

정병묵,이성건,안홍태 嶺南大學校 工業技術硏究所 2002 工業技術硏究所論文集 Vol.30 No.1

In the texture manufacturing process, it is very important to uniformly maintain the thickness of yarn because the quality of texture is affected by dint of the quality of yarn. However, the production of chemical yarn is made of more than 10 strands because of productivity. The united yarn has to be splitted into independent strand before making texture. In this process, most of splitting machine has too heavy and varied tension because of its structural problem. To reduce the tension of yarn, this article proposes a splitting machine with a tension controller. The control algorithm is mainly a rule-based fuzzy logic because of its non-linearity and yarn's high velocity. Using this controller, the tension of yarn is 3 or 4 times lower than that of the traditional splitting machine. Through the development of a tension controlled splitting machine, we can get yarn of good quality and expect high productivity because it is possible to reduce the splitting time of yarn.

원룸소형주택의 효율적 관리를 위한 요구도 조사 - 경기도 광주시를 대상으로 -

정병묵,서충원 한국주거학회 2020 한국주거학회 논문집 Vol.31 No.5

산업화 초 고령화, 핵가족화 등의 사회구조 변화로 인해 1~2인 가구의 증가로 소형주택에 대한 수요가 증가하고 있다. 소형가구는 원룸의 주 수요대상이되면 상대적으로 낮은 소득수준 및 주택에 대한 인식변화, 직장과 근접거리 내 거주선호 등으로 인해 도심권 내 소형임대 주택에 거주하는등 주택선택에 있어서 일반가구와 다른 양상을 보이고 있다. 즉, 원룸과 같은 소형주택의 전국적인 인허가 실적이 서울, 경기도 권역에 집중되어 있으며 이러한 이유가 직장의 집중 현상 및 전월세 주택부족의 대응을 위하여 주차장, 사업승인 적용 완화로 사업성이 제고되면서 재개발,재건축이 어려운 주거지역 내 공급이 확대되었기 때문이라고하였다(OH, 2017) 주택관리 업무영역을 바탕으로 원룸소형주택을 효율적으로 관리할 수 있는 항목을 선정한다면, 원룸소형주택의 관리에 대한 전략적 제고방안 모색에 기초자료를 활용할 수 있을 것이다. 따라서 본 연구에서는 원룸소형주택의 효율적인 관리방안을 조사하여 우선 순위가 높은 항목이 무엇인지를 파악하고자 하였다. The purpose of this study is to find an efficient management plan for small-sized studio housing and to promote the revitalization of small-sized housing. Management items were derived by conducting a preliminary research survey, and questionnaires were produced. The analysis results are as follows. First, as a result of the T-test analysis of the corresponding sample, there were significant differences between the importance and performance of 8 items of safety, 6 items of sociality, 4 items of vitality, 6 items of representativeness, and 6 items of health. Second, the demand was calculated by the Borich demand formula, and the Locus for Focus graph was derived. The priority management items for small-sized studio houses include safety crime prevention management items, safety fire management items, safety electrical facilities safety management items, safety facility maintenance management items, and health-related surrounding odors, hygiene management items, and safety surrounding traffic. Safety management items, representative organization's operation management items, and health status ventilation status management items were shown. Therefore, in order to build and supply a small-sized studio house, it is necessary to accurately grasp the needs of residents and to seek strategic measures to improve residence satisfaction based on high priority management items.

Hybrid Method for Phase-Height Relationship in 3D Shape Measurement using Fringe Pattern Projection

정병묵,박윤창 한국정밀공학회 2014 International Journal of Precision Engineering and Vol. No.

A height estimating function is proposed based on geometric analysis for a three-dimensional (3-D) measurement system using a digital light processing (DLP) projector and a camera. The proposed 3-D shape measurement method is a hybrid method that combines the geometric parameter measuring method and the least squares method. This method uses the phase-to-height relationship for one line by plane analysis, and the related parameters are estimated using the least squares method. The proposed method has one function per image line instead of one function per image pixel. Sinusoidal fringe patterns of the projector are projected on the object, and the phase of the measuring point is calculated from the camera image. Then, the relationship between the phase by fringe patterns and the height of the measuring point is described as a parameter of the horizontal coordinate on the image plane. Thus, the 3-D shape of the object can be obtained. Our experiments show that the error of the modeling function is within ±0.1 mm when the x-z working range is 100×50 mm. Therefore, the proposed method can dramatically reduce the number of mapping functions needed for 3-D measurement using the geometric relationship between the projector and camera.

뉴로 퍼지 모델을 이용한 편향요크의 RGB색 일치에 대한 제어

정병묵(Byeong-Mook Chung),임윤규(Yoon-Kyu Lim),정창욱(Chang-Ook Jung) Korean Society for Precision Engineering 1998 한국정밀공학회지 Vol.15 No.5

GPS 와 비전시스템을 이용한 무인 골프카의 자율주행

정병묵(Byeong Mook Jung),여인주(In Joo Yeo),조지승(Che Seung Cho) Korean Society for Precision Engineering 2009 한국정밀공학회지 Vol.26 No.6