• 융복합기술연구소 논문집
• /
• 제3권2호
• /
• pp.31-37
• /
• 2013

This paper proposes a vision-based inspection algorithm for a punch which is used when forming the head of the small screws. To maintain good quality of punch, the precise inspection of its dimension and the depth of the punch head is important. A CCD camera and an illumination dome light are used to measure its dimensions. And a structured line laser is also used to measure the depth of the punch head. Resolution and visible area depend on setup between laser and camera which is determined using CAD-based simulation. The proposed method is successfully evaluated using experiment on #2 punch.

• 한국컴퓨터정보학회논문지
• /
• 제24권6호
• /
• pp.67-72
• /
• 2019

This paper proposes a computer vision-based banknote recognition system intended to assist the blind. This system is robust and fast in recognizing banknotes on videos recorded with a smartphone on real-life scenarios. To reduce the computation time and enable a robust recognition in cluttered environments, this study segments the banknote candidate area from the background utilizing a technique called Pixel-Based Adaptive Segmenter (PBAS). The Speeded-Up Robust Features (SURF) interest point detector is used, and SURF feature vectors are computed only when sufficient interest points are found. The proposed algorithm achieves a recognition accuracy of 98%, a 100% true recognition rate and a 0% false recognition rate. Although Korean banknotes are used as a working example, the proposed system can be applied to recognize other countries' banknotes.

• 한국정밀공학회지
• /
• 제10권3호
• /
• pp.168-174
• /
• 1993

A new digital image processing method for measuring of the flank wear of cutting tool is presented. The method is based on computer vision technology in which the tool is illuminated by two halogen lamps and the wear zone is visualized using a CCD camera. The image is converted into digital pixel and processed to detect the wearland width. As a conclusion, it has been proved that the average wearland area and mzximum peak values of the flank wear width can monitored effectively to a measuring resolution of 0.01mm.

• 방송공학회논문지
• /
• 제7권3호
• /
• pp.248-261
• /
• 2002

본 논문에서는 스테레오 비젼 시스템의 3차원 정보에 의해 가변되는 윈도우 마스크와 광 BPEJTC(binary phase extraction joint transform correlator)를 이용하여 스테레오 카메라를 제어하는 새로운 3차원 물체추적 시스템을 제안하였다. 즉, 스테레오 비젼 시스템의 구성 요소에 의해 3차원 정보인 추적 물체까지의 거리 정보를 쉽게 구할 수 있고, 이 거리 정보로 윈도우 마스크를 가변 시켜 추적물체 영역을 추출할 수 있다. 이 추적물체 영역은 다음 기준영상으로 갱신하여 사용된다. 그리고 이 기준영상과 스테레오 입력 영상간에 광 BPEJTC를 실행하여 추적 물체의 위치 값을 구하고. 이 값으로 스테레오 카메라의 주시각과 팬/틸트를 제어하여 3차원 물체추적이 이루어진다. 실험 결과 제안한 알고리즘은 스테레오 입력 영상에서 배경잡음과 관계없이 추적 물체영역을 추출하여 3차원 물체추적이 가능하고, 이의 구현으로 3차원 원격작업 시스템이나 적응적인 3차원 물체 추적기 등의 구현 가능성을 제시하였다.

• 한국항공우주학회지
• /
• 제34권7호
• /
• pp.63-70
• /
• 2006

본 논문은 영상기반 헤드 트랙커에 인공 표식의 면적을 이용하는 연구를 기술하였다. 헤드 트랙커 체계는 병진운동과 회전운동으로 구성되어 있으며, 이들은 웹 카메라에 의하여 감지되었다. 감지된 영상은 영상처리 기법과 인공 신경망에 의하여 운동에 따른 결과를 만들게 된다. 헤드 트랙커가 사용될 항공기의 조종석의 특성상 병진운동은 헬멧의 특정 색을 추적하게 하였다. 회전 운동은 인공 신경망을 이용하여 추적하였으며, 헬멧에 표시된 두 가지 색의 면적 비율을 입력 값으로 사용하였다. 여기서 역전파 알고리즘과 RBFN을 사용하였다. 두 알고리즘은 머리의 움직임과 같은 비선형 체계를 분류하고 추적하는데 용이한 알고리즘으로 역전파 알고리즘은 피드백 특성을, RBFN은 확률적 특성을 이용한다. 본 논문에서는 회전운동에 어느 알고리즘이 더 적합한 알고리즘인지 비교하였다.

• Computers and Concrete
• /
• 제33권4호
• /
• pp.425-443
• /
• 2024

Floods are among the most common natural hazards in urban areas. To mitigate the problems caused by flooding, unstructured data such as images and videos collected from closed circuit televisions (CCTVs) or unmanned aerial vehicles (UAVs) have been examined for flood management (FM). Many computer vision (CV) techniques have been widely adopted to analyze imagery data. Although some papers have reviewed recent CV approaches that utilize UAV images or remote sensing data, less effort has been devoted to studies that have focused on CCTV data. In addition, few studies have distinguished between the main research objectives of CV techniques (e.g., flood depth and flooded area) for a comprehensive understanding of the current status and trends of CV applications for each FM research topic. Thus, this paper provides a comprehensive review of the literature that proposes CV techniques for aspects of FM using ground camera (e.g., CCTV) data. Research topics are classified into four categories: flood depth, flood detection, flooded area, and surface water velocity. These application areas are subdivided into three types: urban, river and stream, and experimental. The adopted CV techniques are summarized for each research topic and application area. The primary goal of this review is to provide guidance for researchers who plan to design a CV model for specific purposes such as flood-depth estimation. Researchers should be able to draw on this review to construct an appropriate CV model for any FM purpose.

• 제어로봇시스템학회논문지
• /
• 제10권7호
• /
• pp.649-657
• /
• 2004

A windshield wiper system plays a key part in assurance of driver's safety at rainfall. However, because quantity of rain and snow vary irregularly according to time and velocity of automotive, a driver changes speed and operation period of a wiper from time to time in order to secure enough visual field in the traditional windshield wiper system. Because a manual operation of wiper distracts driver's sensitivity and causes inadvertent driving, this is becoming direct cause of traffic accident. Therefore, this paper presents the basic architecture of vision-based smart wiper system and the rain sensing algorithm that regulate speed and interval of wiper automatically according to quantity of rain or snow. Also, this paper introduces the fuzzy wiper control algorithm based on human's expertise, and evaluates performance of suggested algorithm in the simulator model. Especially the vision sensor can measure wider area relatively than the optical rain sensor, hence, this grasps rainfall state more exactly in case disturbance occurs.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2017년도 춘계공동학술대회
• /
• pp.154-154
• /
• 2017

Root is an important organ of plant that typically lies below the surface of the soil. Root surface determines the ability of plants to absorb nutrient and water from the surrounding soil. This study describes an application of image processing and computer vision which was implemented for rapid measurement of seed germination such as root length, surface area, average diameter, branching points of roots. A CCD camera was used to obtain RGB image of seed germination which have been planted by wet paper in a humidity chamber. Temperature was controlled at approximately 250C and 90% relative humidity. Pre-processing techniques such as color space, binarized image by customized threshold, removal noise, dilation, skeleton method were applied to the obtained images for root segmentation. The various morphological parameters of roots were estimated from a root skeleton image with the accuracy of 95% and the speed of within 10 seconds. These results demonstrated the high potential of computer vision technique for the measurement of seed germination.

• 한국측량학회지
• /
• 제27권1호
• /
• pp.735-742
• /
• 2009

최근들어, 우리나라에서는 수치지도 2.0을 이용하여 전산편집에 의해 종이지도를 제작하고 있다. 그러나 수치지도와 종이지도는 표현방법이 상이하기 때문에 축척에 따라 지도일반화가 처리되어야하며 지도일반화 기준은 사람이 눈으로 직접 판독하는 대상물의 크기에 의해 결정되어야 한다. 이를 위해 본 연구에서는 각 축척의 지도에서 표현되는 건물의 크기를 표준시력의 눈으로 관측하고 그 결과를 분석하였다. 연구결과 인간의 눈에 적합한 건물의 크기는 단변의 길이가 0.4mm이상인 도형의 면적에 해당되며, 지도일반화를 위한 독립건물, 축소건물, 밀집건물처리에 모두 이 기준을 적용하였다.

• 제어로봇시스템학회논문지
• /
• 제6권12호
• /
• pp.1106-1112
• /
• 2000

In this paper, we present a vision system which measures the cross-section of a hot wire-rod in the steel plant. We developed a mobile vision system capable of accurate measurement, which is strong to vibration and jolt when moving. Our system uses green laser light sources and CCD cameras as a sensor, where laser sheet beams form a cross-section contour on the surface of the hot wire-rod and the reflected light from the wire-rode is imaged on the CCD cameras. We use four lasers and four cameras to obtain the image with the complete cross-section contour without an occlusion region. We also perform camera calibrations to obtain each cameras physical parameters by using a single calibration pattern sheet. In our measuring algorithm, distorted four-camera images are corrected by using the camera calibration information and added to generate an image with the complete cross-section contour of the wire-rod. Then, from this image, the cross-section contour of the wire-rod is extracted by preprocessing and segmentation, and its height, width and area are measured.