• 한국측량학회지
• /
• 제37권3호
• /
• pp.167-175
• /
• 2019

물의 색깔 즉, 수색(水色)을 분석하면 그 물이 함유하고 있는 유색 구성물질의 분포 및 농도를 비파괴적으로 추정할 수 있다. 이러한 분석을 위해 분광복사계를 사용하는데, 최근 드론, 자율운행차, 헬리카이트 등의 저고도 무인 플랫폼에 장착하기 위한 경량 다분광 카메라에 대한 수요가 높아지고 있다. 본 연구에서는 최근 활용 용이성으로 인해 지역적 환경 변화를 모니터링함에 있어 그 활용도가 높아진 Micasense사의 Rededge-M 다분광 카메라의 전처리를 수행하고, 수색관측에의 활용성을 검증하기 위한 분석을 수행하였다. 우선, 영상 형태로 생성되는 자료에서의 Vignette 보정 및 밴드 정렬을 수행하였고, 수색관측을 위해 필요한 하늘, 물, 태양광을 측정한 복사량 그리고 그로부터 최종적으로 도출되는 원격탐사 반사도 관측치를 독립적인 초분광 센서의 관측값과 비교하여 분석하였다. 실험 결과, 전처리 과정을 수행하였을 시, 청색밴드(475 nm)와 근적외선 밴드(840 nm)에서 주목할 만한 차이가 있었지만, Rededge-M은 전반적으로 수색 분석을 위한 기본적인 광학적 성능을 가지고 있음을 확인하였다.

• 한국인터넷방송통신학회논문지
• /
• 제24권3호
• /
• pp.77-85
• /
• 2024

본 논문에서는 열화상 카메라, 스피드돔 카메라, PTZ 카메라, 레이더, 라이다 센서와 스마트폰을 통합한 순찰 로봇을 설계하고 구현하였다. 이 로봇은 복잡한 환경에서도 효율적으로 감시하고 대응할 수 있는 능력을 갖추고 있으며, 특히 야간이나 가시성이 낮은 조건에서도 높은 성능을 발휘할 수 있도록 설계되었다. 로봇의 이동성을 위해 궤도 이동체계를 선택하였고, 실시간 데이터 처리와 의사결정을 위해 스마트폰 기반의 제어 시스템을 개발하였다. 다양한 센서의 조합은 로봇이 환경을 포괄적으로 인식하고 위험 요소를 신속하게 감지할 수 있게 해준다. 열화상 카메라는 야간 감시에, 스피드돔과 PTZ 카메라는 광범위한 영역 모니터링에, 레이더와 라이다는 장애물 탐지와 회피에 활용된다. 스마트폰 기반 제어 시스템은 사용자 친화적인 인터페이스를 제공한다. 제안된 로봇 시스템은 보안, 감시, 재난 대응 등 다양한 분야에서 활용 가능하다. 향후 연구에서는 로봇의 자율 순찰 알고리즘 개선, 다중 로봇 협업 시스템 개발, 실제 환경에서의 장기 테스트 등이 수행되어야 할 것이다. 본 연구는 지능형 감시 로봇 분야의 발전에 기여할 것으로 기대된다.

• Smart Structures and Systems
• /
• 제9권3호
• /
• pp.273-286
• /
• 2012

As civil structures are exposed to various external loads, it is essential to assess the structural condition, especially the structural displacement, in every moment. Therefore, a visually servoed paired structured light system was proposed in the previous study. The proposed system is composed of two screens facing with each other, each with a camera, a screen, and one or two lasers controlled by a 2-DOF manipulator. The 6-DOF displacement can be calculated from the positions of three projected laser beams and the rotation angles of the manipulators. In the estimation process, one of well-known iterative methods such as Newton-Raphson or extended Kalman filter (EKF) was used for each measurement. Although the proposed system with the aforementioned algorithms estimates the displacement with high accuracy, it takes relatively long computation time. Therefore, an incremental displacement estimation (IDE) algorithm which updates the previously estimated displacement based on the difference between the previous and the current observed data is newly proposed. To validate the performance of the proposed algorithm, simulations and experiments are performed. The results show that the proposed algorithm significantly reduces the computation time with the same level of accuracy compared to the EKF with multiple iterations.

• 천문학회보
• /
• 제40권1호
• /
• pp.55.3-55.3
• /
• 2015

한국천문연구원에서 개발 중인 KMTNet 망원경은 2014년 칠레(5월), 남아공(8월), 호주(11월)에 설치가 완료되었다. 망원경 설치 이후, 연구관측용 광시야 18k CCD 카메라를 설치하기 전까지의 기간 동안 시험관측용 4k CCD 카메라(STX-16803)를 활용하여 관측을 수행하였다. 시험관측 대상으로는 KMTNet의 주 관측 영역인 우리은하 팽대부처럼 별이 밀집된 영역에서 영상차감법(Difference Image Analysis; DIA)을 활용해 변광하는 천체를 찾기 위해 $25^{\prime}{\times}25^{\prime}$의 CCD 관측 영역에 적당한 6개의 남반구 구상성단을 선정하였다. 본 발표에서는 관측된 성단의 측광 결과와 영상차감법을 이용해 찾은 변광성에 대해 논의할 예정이다.

• 한국정밀공학회지
• /
• 제31권7호
• /
• pp.561-567
• /
• 2014

Precision injection mold is an essential element in order to manufacture small and precision plastic lenses used for phone camera. There are many critical factors to meet the requested specifications of high quality plastic lenses. One of the main issues to realize high quality is minimizing decenter value, which becomes more critical as pixel numbers increases. This study suggests the method to minimize decenter value by modifying ejecting structure of the mold. Decenter value of injection-molded lens decreased to 1 ${\mu}m$ level from 5 ${\mu}m$ by applying suggested ejecting method. Also, we also developed BIS (Built-in Sensor) based smart mold system, which has pressure and temperature sensors inside of the mold. Pressure and temperature profiles from cavities are obtained and can be used for deduction of optimal injection molding condition, filling imbalance evaluation, status monitoring of injection molding and prediction of lens quality.

• 대한기계학회논문집A
• /
• 제21권9호
• /
• pp.1531-1540
• /
• 1997

Mordern industrial society pursues unmanned system and automation of manufacturing process. Abreast with this tendensy, production of goods which requires advanced accuracy is increasing as well. According to this, the work sensing time of dressing by monitoring and diagnosing the condition of grinding, which is th representative way in accurate manufacturing, is an important work to prevent serious damages which affect grinding process or products by wearing grinding wheel. Computer vision system was composed, so that grinding wheel surface was acquired by CCD camera and the change of cutting edge ratio was measured. Then we used automatic thresholding technique from histogram as a way of dividing grinding cutting edge from grinding surface. As a result, we are trying to approach unmanned system and automation by deciding more accurate time of dressing and by visualizing behavior of grinding wheel by making use of computer vision.

• ETRI Journal
• /
• 제37권2호
• /
• pp.395-405
• /
• 2015

We address the problem of uncooperative person recognition through continuous monitoring. Multiple modalities, such as face, height, clothes color, and voice, can be used when attempting to recognize a person. In general, not all modalities are available for a given frame; furthermore, only some modalities will be useful as some frames in a video sequence are of a quality that is too low to be able to recognize a person. We propose a method that makes use of stochastic information updates of temporal modalities and environment estimators to improve person recognition performance. The environment estimators provide information on whether a given modality is reliable enough to be used in a particular instance; such indicators mean that we can easily identify and eliminate meaningless data, thus increasing the overall efficiency of the method. Our proposed method was tested using movie clips acquired under an unconstrained environment that included a wide variation of scale and rotation; illumination changes; uncontrolled distances from a camera to users (varying from 0.5 m to 5 m); and natural views of the human body with various types of noise. In this real and challenging scenario, our proposed method resulted in an outstanding performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1244-1248
• /
• 2003

This paper describes visual tracking procedure of the underwater mobile robot for nuclear reactor vessel inspection, which is required to find the foreign objects such as loose parts. The yellowish underwater robot body tends to present a big contrast to boron solute cold water of nuclear reactor vessel, tinged with indigo by Cerenkov effect. In this paper, we have found and tracked the positions of underwater mobile robot using the two color information, yellow and indigo. The center coordinates extraction procedures are as follows. The first step is to segment the underwater robot body to cold water with indigo background. From the RGB color components of the entire monitoring image taken with the color CCD camera, we have selected the red color component. In the selected red image, we extracted the positions of the underwater mobile robot using the following process sequences; binarization, labelling, and centroid extraction techniques. In the experiment carried out at the Youngkwang unit 5 nuclear reactor vessel, we have tracked the center positions of the underwater robot submerged near the cold leg and the hot leg way, which is fathomed to 10m deep in depth.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.260-263
• /
• 2003

This paper has developed the computer integration manufacturing system and Internet based tele-operations. The functions of CIMS include production planing, material requirement planning, work order generation, process control, quality control, shipping planning, warehouse and inventory management and material cost accounting.[1] In this paper focuses on the automatic warehouse control and inventory management by developing the information system as well as the Internet-based integration. The system overview is divided into three parts, the mechanical system, the computer and developed software to control and manage the information and the communication system. The mechanical system consists of the warehouse machine and forklift mobile robot controlled by programmable logic controller (PLC). The computer works on many functions such as control station interfaces with PLC, managing database and inventory, and Internet server to broadcast the inventory database to users via World Wide Web and monitoring the operation on web camera. Our scheme the inventory database can be checked easily anywhere and anytime when the users connect to the Internet. In this article, the lead-time and inventory level can be reduced therefore the holding cost and operating time is also decreased.

• 로봇학회논문지
• /
• 제12권3호
• /
• pp.313-321
• /
• 2017

One of the most frequently performed tasks in human-robot interaction (HRI), intelligent vehicles, and security systems is face related applications such as face recognition, facial expression recognition, driver state monitoring, and gaze estimation. In these applications, accurate head pose estimation is an important issue. However, conventional methods have been lacking in accuracy, robustness or processing speed in practical use. In this paper, we propose a novel method for estimating head pose with a monocular camera. The proposed algorithm is based on a deep neural network for multi-task learning using a small grayscale image. This network jointly detects multi-view faces and estimates head pose in hard environmental conditions such as illumination change and large pose change. The proposed framework quantitatively and qualitatively outperforms the state-of-the-art method with an average head pose mean error of less than $4.5^{\circ}$ in real-time.