• 한국ITS학회 논문지
• /
• 제7권5호
• /
• pp.64-76
• /
• 2008

근본적인 교차로에서의 안전도 향상을 위해서는 사고발생 이전에 나타나는 사고의 개연성에 대한 연구가 필요하다. 교통사고는 교통상충상황의 연장선에서 발생하는 것으로써, 적은 시간과 한정된 공간에서 조사가 용이하고 자료취득이 수월하며 적은 비용으로 연구를 수행할 수 있다는 장점이 있다. 따라서 교통상충기법은 그 활용도가 높으며, 많은 필요성이 제기되고 있는 실정이다. 이에 본 연구에서는 신호교차로 영상을 입력받아서 교통상충을 자동으로 분석하고 처리할 수 있는 프로그램을 개발하였다. 본 프로그램은 CCTV카메라에서 입력되는 영상입력부, 입력된 영상을 배경영상, 현재영상, 차영상(difference image), 이동차량 분할(segmentation)영상을 저장하는 영상저장부, 저장된 영상을 상충알고리즘에 의해 상충판단을 하는 영상처리부, 그 처리된 결과는 디스플레이 해주는 영상출력부로 구분하여 처리한다. 프로그램 개발은 그래픽 언어인 LabVIEW 8.5버전과 VISION모듈 라이브러리를 이용하여 개발하였다.

• 한국기계가공학회지
• /
• 제8권2호
• /
• pp.3-9
• /
• 2009

When washing machine is rotated in the laundry, it tends to lean toward one side. This tendency causes a serious vibration. The balance of washing machine plays an important role in order to reduce the vibration by injecting the sand or the salt water into the balance of washing machine. The hot plate welder is used to prevent from outflow of contents. The hot plate welder brings about many problems which is concerned with accidents. The direction recognition and location information of the balance are required in this system. In this paper, the recognition direction of balance in washing machine using machine vision system is studied. The template matching algorithm compares sub-image with original image acquired in real-time to obtain a center point of balance image. The mid points and the edges of balance are estimated by the edge detection and gauging algorithms. The data acquired by these results is used for recognition direction of balance. The automation software for image processing is developed by using LabVIEW.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.447-450
• /
• 2011

This paper shows the application of P-N Learning [4] method in the soccer ball detection and improvement for increasing the speed of processing. In the P-N learning, the learning process is guided by positive (P) and negative (N) constraints which restrict the labeling of the unlabeled data, identify examples that have been classified in contradiction with structural constraints and augment the training set with the corrected samples in an iterative process. But for the long-view in the soccer game, P-N learning will produce so many ferns that more time is spent than other methods. We propose that color histogram of each frame is constructed to delete the unnecessary details in order to decreasing the number of feature points. We use the mask to eliminate the gallery region and Line Hough Transform to remove the line and adjust the P-N learning's parameters to optimize accurate and speed.

• 한국생산제조학회지
• /
• 제22권1호
• /
• pp.150-155
• /
• 2013

This work present a new method of sealing inspection system for vehicle in which foam rubber materials are used for sealing the vehicle parts. This system is composed from a devices comprising non-contact and real-time scanning on visual inspection in machine parts. We have been investigated qualitative factors that influenced on sealing system of vehicle structure which flexibly attenuated vibration and plenty of foam rubber materials having elastic property. However, there are different factors which still depended on outdated technique (personnel subjective judgment) in the performance inspection of rubber parts, specially for cross section inspection. Through a newly developed inspection system which recently applied for the production line, we successfully achieved more effective results of matching rate by about 80 % in the sealing performance inspection with 0.7% to 1.4% in the repeated errors. These are resulted from non-contacted response by CCD camera and vision program using geometry matching method. We expect that this system may be widely applied in the strict inspection parts of more diverse cross-section in future.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.II
• /
• pp.318-324
• /
• 2000

Ultrasonic and magnetic resonance imaging systems are used to visualize the interior states of biological objects. These nondestructive methods have many advantages but too much expensive. And they do not give exact color information and may miss some details. If it is allowed to destruct some biological objects to get the interior and exterior information, constructing 3D image from the series of the sliced sectional images gives more useful information with relatively low cost. In this paper, PC based automatic 3D model generator was developed. The system was composed of three modules. One is the object handling and image acquisition module, which feeds and slices objects sequentially and maintains the paraffin cool to be in solid state and captures the sectional image consecutively. The second is the system control and interface module, which controls actuators for feeding, slicing, and image capturing. And the last is the image processing and visualization module, which processes a series of acquired sectional images and generates 3D graphic model. The handling module was composed of the gripper, which grasps and feeds the object and the cutting device, which cuts the object by moving cutting edge forward and backward. Sliced sectional images were acquired and saved in the form of bitmap file. The 3D model was generated to obtain the volumetric information using these 2D sectional image files after being segmented from the background paraffin. Once 3-D model was constructed on the computer, user could manipulate it with various transformation methods such as translation, rotation, scaling including arbitrary sectional view.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 춘계학술대회 논문집
• /
• pp.824-828
• /
• 2007

With increasing interest in the reduction of cost for operation and maintenance of overhead catenary system, various methods of condition monitoring have been developed and used in with high-speed analysis and advanced image processing techniques. This study utilizes a high-speed camera as inspecting system to measure the wear, stagger, hight and arc extinguishing test of overhead catenary system. All measuring image were captured by a high speed CMOS camera with PCI express output, which can acquire up to 1000 frames per second with the resolution 1024 × 1280 pixels. Line type laser source with a power equal to 300 mW and the National Instrument LabVIEW (8.0) based on vision acquisition software have been used in application programming interface for image acquisition, display, and storage. The proposed high-speed camera system is finally applied to measure the overhead catenary system showing promising on-field applications

• 전기전자학회논문지
• /
• 제17권4호
• /
• pp.398-406
• /
• 2013

핵의학 영상 기기인 양전자 방출 단층 촬영 장치(Positron emission tomography: PET)와 같은 진단기기는 방사성의약품을 인체에 주입하여 질병을 진단한다. 이 때 사용되는 방사성의약품은 안전성을 위하여 적절한 수소 이온농도를 가져야 한다. 일반적으로 방사성 의약품의 수소 이온 농도를 측정하는 과정에서 흔히 사용되는 것이 pH시험지이다. 표본을 pH 시험지에 떨어뜨려 pH 시험지의 변색 정도를 표준색상표(Standard color chart)와 비교하여 표본의 pH를 알 수 있다. 그러나 이 방법은 측정자의 경험 정도에 따라 pH 측정값에 차이가 발생할 수 있다. 또한 pH 메타기는 고감도의 센서를 사용함으로 오염에 주의해야 한다. 이러한 불편함을 고려하여 쉽고 간단하게 정확한 pH를 측정하기 위한 새로운 장치 제작과 영상 기반 알고리즘을 통한 소프트웨어를 개발하였다. 이렇게 개발한 장치는 최종적으로 방사성의약품의 생산 시 품질관리(QC) 통합 제어 시스템으로 사용된다.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2006년도 하계학술대회 논문집 Vol.7
• /
• pp.543-544
• /
• 2006

This paper describes a simple real-time monitoring system for use in measurement subsystem of contact wire and geometry of overhead contact wire in electric railway. The system has been consists of a high speed CMOS camera with resolution $1024\;{\times}\;1280$ pixels, line type laser source with a power equal to 300 mW, and PC-based image acquisition system with PCI Express slot. National instrument LabVIEW (8.0) and vision acquisition software have been used in application programming interface for image acquisition, display, and storage with a frequency of sampling of 500 acquisitions per second.

• Journal of Welding and Joining
• /
• 제30권4호
• /
• pp.38-43
• /
• 2012

Using a fiber laser heat source, an oil pressure sensor was fabricated to measure the pressure in commercial vehicles. A stepping motor was used for the rotational and translational motion in the diaphragms and hardware joining. Laser welding process algorism including shielding gas control and vision system was integrated by using LabVIEW software for the high quality welding and in-line monitoring purpose. For the maximum flexibility in pressure transmission to the pressure sensor, thin sheet metal diaphragm, $25{\sim}50{\mu}m$(SUS-316L), was used and the diaphragms were optimally designed with FEM analysis. The welded samples were cross-sectioned the observation showed that the maximum depth ratio was more than seven times of diaphragms. The maximum welding speed was measured to be as high as 50in/mm by the developed automation mechanism. The fabricated prototypes were tested for the proof pressure, spring constant and sealing. The FEM results of spring constant measurement was as accurate as up to 80% of the design value and the sensor was safely operated up to the nominal pressure of 10bars.

• 한국컴퓨터그래픽스학회논문지
• /
• 제23권3호
• /
• pp.31-38
• /
• 2017

본 논문에서는 도심 영상에 대해 맨하탄 좌표계를 추정하는 합성곱 신경망(Convolutional Neural Network) 기반의 시스템을 제안한다. 도심 영상에서 맨하탄 좌표계를 추정하는 것은 영상 조정, 3차원 장면 복원 등 컴퓨터 그래픽스 및 비전 문제 해결의 기본이 된다. 제안하는 합성곱 신경망은 GoogLeNet[1]을 기반으로 구성한다. 합성곱 신경망을 훈련하기 위해 구글 스트리트 뷰 API로 영상을 수집하고 기존 캘리브레이션 방법으로 맨하탄 좌표계를 계산하여 데이터셋을 생성한다. 장면마다 새롭게 합성곱 신경망을 학습해야하는 PoseNet[2]과 달리, 본 논문에서 제안하는 시스템은 장면의 구조를 학습하여 맨하탄 좌표계를 추정하기 때문에 학습되지 않은 새로운 장면에 대해서도 맨하탄 좌표계를 추정한다. 제안하는 방법은 학습에 참여하지 않은 구글 스트리트 뷰 영상을 검증 데이터로 테스트하였을 때 $3.157^{\circ}$의 중간 오차로 맨하탄 좌표계를 추정하였다. 또한, 동일 검증 데이터에 대해 제안하는 방법이 기존 맨하탄 좌표계 추정 알고리즘[3]보다 더 낮은 중간 오차를 보이는 것을 확인하였다.