능동 객체에 기반을 둔 제조 공정 환경에서의 컴퓨터 시각 시스템 통합

이동우,장덕진,이용진 우송대학교 1997 우송대학교 논문집 Vol.2 No.-

제조 공정 환경에서의 시스템 통합이란 단순히 부속 시스템들이 함께 동작하는 것을 의미하는 것이 아니고, 기업의 사업 목표를 이루기 위해 함께 일하는 것을 의미한다. 즉, 각 부속 시스템들이 지능적으로 동작하고 다른 시스템들과 적극적으로 협동하는 것이다. 본 논문은 최근 그 응용이 크게 증가하고 있는 컴퓨터 시각 시스템 관점에서 제조공정 시스템들의 통합 문제를 다룬다. 이러한 통합 시스템을 이루기 위해서, 기존의 객체지향 패러다임(paradigm)을 포괄하는 능동 객체 패러다임을 제안한다. 통합된 시스템은 능동 객체와 수동 객체로 분류되는 객체들로 구축된다. 또한, 통합된 시각 시스템의 원형(protype) 시스템 구축을 위한 초기 구조(framework)를 제시한다. The meaning of the integration in manufacturing environments is that all component systems to meet the company business objectives rather than simply work together. Each component should behave intelligently and actively cooperate with other systems. The issues of integration of an manufacturing system are investigated in perspective of a computer vision system which has found an increasing number of applications. To achieve the integration, active object paradigm is proposed, which subsumes conventional object-oriented paradigm. The integrated system is implemented as a collection of objects which are classified into active objects and passive objects. An initial framework for the prototype implementation for an integrated computer vision system is presented.

Vision-based Input-Output System identification for pedestrian suspension bridges

Jeonghyeok Lim,Hyungchul Yoon 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.29 No.5

Recently, numbers of long span pedestrian suspension bridges have been constructed worldwide. While recent tragedies regarding pedestrian suspension bridges have shown how these bridges can wreak havoc on the society, there are no specific guidelines for construction standards nor safety inspections yet. Therefore, a structural health monitoring system that could help ensure the safety of pedestrian suspension bridges are needed. System identification is one of the popular applications for structural health monitoring method, which estimates the dynamic system. Most of the system identification methods for bridges are currently adapting output-only system identification method, which assumes the dynamic load to be a white noise due to the difficulty of measuring the dynamic load. In the case of pedestrian suspension bridges, the pedestrian load is within specific frequency range, resulting in large errors when using the output-only system identification method. Therefore, this study aims to develop a system identification method for pedestrian suspension bridges considering both input and output of the dynamic system. This study estimates the location and the magnitude of the pedestrian load, as well as the dynamic response of the pedestrian bridges by utilizing artificial intelligence and computer vision techniques. A simulation-based validation test was conducted to verify the performance of the proposed system. The proposed method is expected to improve the accuracy and the efficiency of the current inspection and monitoring systems for pedestrian suspension bridges.

자동차 부품 품질검사를 위한 비전시스템 개발과 머신러닝 모델 비교

박영민,정동일 국제문화기술진흥원 2022 The Journal of the Convergence on Culture Technolo Vol.8 No.1

In computer vision, an image of a measurement target is acquired using a camera. And feature values, vectors, and regions are detected by applying algorithms and library functions. The detected data is calculated and analyzed in various forms depending on the purpose of use. Computer vision is being used in various places, especially in the field of automatically recognizing automobile parts or measuring the quality. Computer vision is being used as the term machine vision in the industrial field, and it is connected with artificial intelligence to judge product quality or predict results. In this study, a vision system for judging the quality of automobile parts was built, and the results were compared by applying five machine learning classification models to the produced data.

위조번호판 부착 차량 출입 방지를 위한 인공지능 기반의 주차관제시스템 개선 방안

장성민,이정우,박종혁 한국지능정보시스템학회 2022 지능정보연구 Vol.28 No.2

Recently, artificial intelligence parking control systems have increased the recognition rate of vehicle license plates using deep learning, but there is a problem that they cannot determine vehicles with fake license plates. Despite these security problems, several institutions have been using the existing system so far. For example, in an experiment using a counterfeit license plate, there are cases of successful entry into major government agencies. This paper proposes an improved system over the existing artificial intelligence parking control system to prevent vehicles with such fake license plates from entering. The proposed method is to use the degree of matching of the front feature points of the vehicle as a passing criterion using the ORB algorithm that extracts information on feature points characterized by an image, just as the existing system uses the matching of vehicle license plates as a passing criterion. In addition, a procedure for checking whether a vehicle exists inside was included in the proposed system to prevent the entry of the same type of vehicle with a fake license plate. As a result of the experiment, it showed the improved performance in identifying vehicles with fake license plates compared to the existing system. These results confirmed that the methods proposed in this paper could be applied to the existing parking control system while taking the flow of the original artificial intelligence parking control system to prevent vehicles with fake license plates from entering.

Stabilized Adaptive Sampling Control for Reliable Real-Time Learning-based Surveillance Systems

김도현,박수현,김중헌,방재영,정소이 한국통신학회 2021 Journal of communications and networks Vol.23 No.2

In modern security systems such as CCTV-based surveillance applications, real-time deep-learning based computer vision algorithms are actively utilized for always-on automated execution. The real-time computer vision system for surveillance applications is highly computation-intensive and exhausts computation resources when it performed on the device with a limited amount of resources. Based on the nature of Internet-of-Things networks, the device is connected to main computing platforms with offloading techniques. In addition, the real-time computer vision system such as the CCTV system with image recognition functionality performs better when arrival images are sampled at a higher rate because it minimizes missing video frame feeds. However, performing it at overwhelmingly high rates exposes the system to the risk of a queue overflow that hampers the reliability of the system. In order to deal with this issue, this paper proposes a novel queue aware dynamic sampling rate adaptation algorithm that optimizes the sampling rates to maximize the computer vision performance (i.e., recognition ratio) while avoiding queue overflow under the concept of Lyapunov optimization framework. Through extensive system simulations, the proposed approaches are shown to provide remarkable gains.

반사식 반사경 유리 결함검사 방법의 개발

편영식 선문대학교 1999 공과대학논문집 Vol.1 No.2

본 연구에서는 Computer Vision의 기술을 반사경 유리의 결함 검사 시스템 개발을 위하여 응용하였다. 지난 연구에서는 반사경 유리의 아래 방향에서 빛을 방사시키며 반사경 유리를 투과한 빛을 CCD카메라에서 검출하는 방식을 사용하였다. 이와 같은 방식에서는 핀흘 곁함이나 스크레치 결함등을 검출할 수 있지만 조개무늬 결함과 유리면의 깨짐 결함의 경우에는 결함검사가 대단히 어려웠다. 이러한 문제점을 해결하기 위하여 반사경 유리의 윗 방향에서 빛을 방사시키면서 반사경 유리를 반사하는 빛을 CCD카메라에서 검출하는 방식을 사용하였다. 조개무늬 결함과 유리면의 깨짐 결함에 대한 검사결과 신뢰도와 정확도가 아주 향상이 되었다. Vision technology is applied to develop a inspection system of optical glass. In our previous development, the lights was built below the workpiece and the CCD camera which built above collected the light which passed the workpiece. But the snell formed defect and glass crack defect could not inspected reliablly. In order to solve these problems, the lights and CCD camera are built above the workpiece and the reflected lights on the optical glass of glass is collected into CCD camera. Reliable results for the inspection of the snell formed defect and glass crack defect are proceesed through this development.

비전 기반 피아노 자동 채보 시스템

박상욱,박시현,박천수 한국전기전자학회 2019 전기전자학회논문지 Vol.23 No.1

Most of music-transcription systems that have been commercialized operate based on audio information. However,these conventional systems have disadvantages of environmental dependency, equipment dependency, and time latency. This paper studied a vision-based music-transcription system that utilizes video information rather than audioinformation, which is a traditional method of music-transcription programs. Computer vision technology is widely usedas a field for analyzing and applying information from equipment such as cameras. In this paper, we created a programto generate MIDI file which is electronic music notes by using smart-phone cameras to record the play of piano. 현재 상용화된 악보 채보 프로그램은 오디오 정보를 기반으로 채보를 진행한다. 이러한 기존 채보 프로그램은 환경 의존성, 장비 의존성, 시간 지연이라는 단점을 지니고 있다. 본 논문은 기존의 오디오를 이용하여 채보를 방식을 지양하고, 연주영상을 분석하여 채보를 진행하는 컴퓨터 비전 기반 악보 채보 시스템을 제안한다. 제안하는 악보 채보 시스템은 대중화된스마트폰 카메라를 활용하여 피아노 연주를 촬영하고, 이를 분석하여 자동으로 전자 악보인 미디파일을 생성하는 방식으로동작한다. 컴퓨터 실험에서 제안하는 악보 채보 시스템은 95.6%의 정확도로 연주된 음계를 채보하는 것으로 조사되었다.

스펙트럼 해석을 이용한 연삭숫돌 마멸거동

유은이(Eun Yi Yu),사승윤(Seung Yoon Sa),유봉환(Bong Hwan Ryu) 한국공작기계학회 1999 한국공작기계학회지 Vol.8 No.5

Grinding System is very difficult to examine closely wear phenomenon or dynamic characterastic, because it is very complex and different from a general cutting system. Considering automatization and precision, it is very important to examine closely grinding system. In this study, grinding wheel surface is acquired by using computer vision system in order to explain wear and loading phenomenon. We investigate the relationship between wear and Fourier spectrum of acquired image, and observe the entropy variation in the process of manufacturing.

간단한 기구부와 결합한 공간증강현실 시스템의 샘플 기반 제어 방법

이아현(Ahyun Lee),이주호(Joo-Ho Lee),이주행(Joo-Haeng Lee) (사)한국CDE학회 2014 한국CDE학회 논문집 Vol.19 No.4

A robotic sapatial augmented reality (RSAR) system, which combines robotic components with projector-based AR technique, is unique in its ability to expand the user interaction area by dynamically changing the position and orientation of a projector-camera unit (PCU). For a moving PCU mounted on a conventional robotic device, we can compute its extrinsic parameters using a robot kinematics method assuming a link and joint geometry is available. In a RSAR system based on user-created robot (UCR), however, it is difficult to calibrate or measure the geometric configuration, which limits to apply a conventional kinematics method. In this paper, we propose a data-driven kinematics control method for a UCR-based RSAR system. The proposed method utilized a pre-sampled data set of camera calibration acquired at sufficient instances of kinematics configurations in fixed joint domains. Then, the sampled set is compactly represented as a set of B-spline surfaces. The proposed method have merits in two folds. First, it does not require any kinematics model such as a link length or joint orientation. Secondly, the computation is simple since it just evaluates a several polynomials rather than relying on Jacobian computation. We describe the proposed method and demonstrates the results for an experimental RSAR system with a PCU on a simple pan-tilt arm.

YOLO알고리즘을 활용한 시각장애인용 식사보조 시스템 개발

이군호(Gun-Ho Lee),문미경(Mi-Kyeong Moon) 한국전자통신학회 2021 한국전자통신학회 논문지 Vol.16 No.5

시각이 온전한 사람들은 식사를 할 때 시각에 대한 의존도를 깊게 인지하지 못한다. 그러나 시각장애인은 식단에 어떤 음식이 있는지 알지 못하기 때문에 옆에 있는 보조인이 시각장애인 수저로 음식의 위치를 시계 방향 또는 전후좌우 등 일정한 방향으로 설명하여 그릇 위치를 확인한다. 본 논문에서는 시각장애인이 스마트폰의 카메라를 이용하여 자신의 식단을 비추면 각각의 음식 이미지를 인식하여 음성으로 음식의 이름을 알려 주는 식사보조 시스템의 개발 내용에 대해 기술한다. 이 시스템은 음식과 식기도구(숟가락)의 이미지를 학습한 YOLO모델을 통해 숟가락이 놓인 음식을 추출해 내고, 이 음식이 무엇인지를 인식하여 이를 음성으로 알려준다. 본 시스템을 통해 시각장애인은 식사보조인의 도움없이 식사를 할 수 있음으로써 자립의지와 만족도를 높일 수 있을 것으로 기대한다. Normal people are not deeply aware of their dependence on sight when eating. However, since the visually impaired do not know what kind of food is on the table, the assistant next to them holds the blind spoon and explains the position of the food in a clockwise direction, front and rear, left and right, etc. In this paper, we describe the development of a meal assistance system that recognizes each food image and announces the name of the food by voice when a visually impaired person looks at their table using a smartphone camera. This system extracts the food on which the spoon is placed through the YOLO model that has learned the image of food and tableware (spoon), recognizes what the food is, and notifies it by voice. Through this system, it is expected that the visually impaired will be able to eat without the help of a meal assistant, thereby increasing their self-reliance and satisfaction.