• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.6
• /
• pp.65-72
• /
• 2009

This paper presents a vision based localization method for indoor mobile robots using the types of vertices from a monocular image. In the images captured from a camera of a robot, the types of vertices are determined by searching vertical edges and their branch edges with a geometric constraints. For obtaining correspondence between the comers of a 2-D map and the vertex of images, the type of vertices and geometrical constraints induced from a geometric analysis. The vertices are matched with the comers by a heuristic method using the type and position of the vertices and the comers. With the matched pairs, nonlinear equations derived from the perspective and rigid transformations are produced. The pose of the robot is computed by solving the equations using a least-squares optimization technique. Experimental results show that the proposed localization method is effective and applicable to the localization of indoor environments.

• Tuberculosis and Respiratory Diseases
• /
• v.48 no.6
• /
• pp.870-878
• /
• 2000

Background : We have studied the $^{67}Ga$ SPECT to determine the activity of pulmonary tuberculosis, especially in patients with minimal extent of the disease on chest radiographs. Because active minimal pulmonary tuberculosis is sometimes difficult to diagnose by means of initial chest X-ray, sputum examination and $^{67}Ga$ planar imaging, we compared $^{67}Ga$ planar imaging with SPECT to evaluate minimal pulmonary tuberculosis activity. Methods : $^{67}Ga$ planar imagings and SPECTs of 69 patients suspected of minimal pulmonary tuberculosis by the initial chest X-ray were performed and compared to each other. Active pulmonary tuberculosis was defined by a positive AFB smear and/or culture in the sputum and changes shown on the serial chest X-ray findings. Results : 1) $^{67}Ga$ planar imaging imagings showed positive uptakes in 24 patients and no uptakes in 13 patients, patients, which confirms active pulmonary tuberculosis. But SPECT imagings showed positive uptakes in 25 patients and no uptakes in 12 patients. 2) Patients confirmed with inactive pulmonary tuberculosis showed no uptake on $^{67}Ga$ planar imaging. Only one of the 32 patients confirmed as having inactive pulmonary tuberculosis showed positive uptake on $^{67}Ga$ SPECT imaging. Conclusions : According to the results of our study, $^{67}Ga$ planar imaging and SPECT are both sensitive in detecting the activity of minimal pulmonary tuberculosis. The difference between the two methods is not statistically significant, and the negative predictive value of the $^{67}Ga$ SPECT is not higher than that of $^{67}Ga$ planar imaging.

• Journal of Biomedical Engineering Research
• /
• v.25 no.5
• /
• pp.335-342
• /
• 2004

This paper describes a trans-admittance scanner for breast cancer detection. A FPGA-based sinusoidal waveform generator produces a constant voltage. The voltage is applied between a hand-held electrode and a scan probe placed on the breast. The scan probe contains an 8x8 array of electrodes that are kept at the ground potential. Multi-channel precision digital ammeters using the phase-sensitive demodulation technique were developed to measure the exit current from each electrode in the array. Different regions of the breast are scanned by moving the probe on the breast. We could get trans-admittance images of resistor and saline phantoms with an anomaly inside. The images provided the information on the depth and location of the anomaly. In future studies, we need to improve the accuracy through a better calibration method. We plan to test the scanner's ability to detect a cancer lesion inside the human breast.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.5
• /
• pp.30-42
• /
• 2022

Due to the increase in construction of tunnels, the burdens of maintenance works for tunnel structures have been increasing in Korea. In addition, the increase of traffic volume and aging of materials also threatens the safety of tunnel facilities, therefore, maintenance costs are expected to increase significantly in the future. Accordingly, automated condition assessment technologies like image-based tunnel scanning system for inspection and diagnosis of tunnel facilities have been proposed. For image-based tunnel scanning system, it is key to create a planar image through stitching of multiple images captured by tunnel scanning system. In this study, performance of feature-based stitching algorithms suitable for stitching tunnel scanning images was evaluated. In order to find a suitable algorithm SIFT, ORB, and BRISK are compared. The performance of the proposed algorithm was determined by the number of feature extraction, calculation speed, accuracy of feature matching, and image stitching result. As for stitching performance, SIFT algorithm was the best in all parts of tunnel image. ORB and BRISK also showed satisfactory performance and short calculation time. SIFT can be used to generate precise planar images. ORB and BRISK also showed satisfactory stitching results, confirming the possibility of being used when real-time stitching is required.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.7
• /
• pp.4405-4410
• /
• 2015

Two-dimensional displacements are obtained from the sandwiched patterns, which superpose two linearly-periodic patterns orthogonally, respectively. The transparent top pattern is identified by deflection of the laser beam due to a difference of refractivity and the opaque bottom pattern is identified by deviation of the beam intensity due to a difference of reflectance. In the sample setup, the top pattern made up of build-up film is manufactured by UV laser machining and the bottom pattern is manufactured by ultra-precision trench machining and deposition for aluminum plate. The proposed decoding method is verified experimentally using the $10{\mu}m$ equally spaced sample patterns and the devised optical system. The Korea Academia-Industrial cooperation Society.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.12
• /
• pp.1225-1230
• /
• 2016

This paper deals with performing missions of a small biped robot using image processing. Localization is required for stable walking under a given map. Localization of the robot is done by extracting boundary on a driving course. Estimation of three parameters including location and orientation is required when walking on a plane. In this paper, two parameters including the location of the robot along the vertical direction of robot's walking direction and an orientation is estimated for localization. Color is used for the detection of obstacles and normalized values are used for the stable detection.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.141-142
• /
• 2008

본 논문은 텍스처된 3차원 점군데이터를 효율적으로 모델링하는 방법을 제안한다. 지상라이다로부터 획득한 3차원 점군데이터는 많은 노이즈를 가지고 있으며 이로 인해 자동적인 모델링이 어렵다. 3차원 모델링에 있어서 메쉬를 생성해야 3차원 랜더링이 가능하지만 3차원 메쉬 생성은 노이즈에 취약하기 때문에 디자이너들이 수작업으로 노이즈를 제거해야만 한다. 하지만 노이즈 자제가 지상 라이다로부터 들어온 데이터이기 때문에 자동적인 노이즈 제거가 어렵다. 본 논문에서는 텍스처된 지상 라이다 데이터로부터 칼라 영상의 정보를 이용한 윤곽선 정보 검출 방법을 제안한다. 대부분의 건물과 같은 구조물에서 최 외곽은 같은 색의 정보를 가지고 있다. 최 외곽 칼라의 정보를 이용하여 칼라 정보의 변화를 제한하고, 유사 칼라 정보를 가지고 있는 픽셀만 얻어냄으로써 최외각 정보를 얻어낸다. 칼라 이미지를 이용만 필터링 된 점군데이터는 xy, xz, yz 각각의 평면에서 윤곽선 데이터를 가지며 이는 구조물에 대한 모델링의 속도를 빠르게 해준다.

• The Journal of the Korea Contents Association
• /
• v.10 no.5
• /
• pp.20-28
• /
• 2010

In this paper, we propose a hand gesture interface for the manipulation of augmented objects in 3D space using a camera. Generally a marker is used for the detection of 3D movement in 2D images. However marker based system has obvious defects since markers are always to be included in the image or we need additional equipments for controling objects, which results in reduced immersion. To overcome this problem, we replace marker by planar hand shape by estimating the hand pose. Kalman filter is for robust tracking of the hand shape. The experimental result indicates the feasibility of the proposed algorithm for hand based AR interfaces.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.345-349
• /
• 2023

In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.1789-1793
• /
• 2008

전자파표면유속계는 홍수유속측정을 위하여 개발된 기기로 평 갈수기에는 유속측정이 불가하여 프로펠러 유속계를 이용하고 있다. 현재 보급된 전자파표면유속계는 하천의 흐름방향에 나란하게 설치하였을 때에만 유속을 측정할 수 있는 기기의 구조상의 한계성 때문에 교량이 없는 지점에서는 유속측정이 불가하여 유량산정을 할 수가 없다. 또한 편각측정이 불가능하여 기기를 각 측선마다 이동 설치하여야 하기 때문에 유속측정시 효율성 떨어진다. 이에 홍수시 유량측정의 효율성을 증대시키고 전자파표면유속계의 활용도를 높이고자 편각측정이 가능하도록 전자파표면유속계의 성능을 개선하는 것이 본 연구의 주된 목적이다. 전자파표면 유속계에서의 편각 측정은 하천의 유속방향을 기준으로 정면에서 측정하면 수평 편각이 0도가 되며 좌우로 안테나를 회전하여 움직인 각도가 측정 편각으로 결정된다. 현장에서 전자파표면유속계의 사용시 편의성을 높이고 유량측정을 효율적으로 하기 위해서는 가급적 편각을 크게 해서 측정을 해야 하지만, 편각이 증가하면 전자파의 물리적 특성 때문에 반사된 신호의 수신 크기가 감소하여 측정이 불가능하게 된다. 이러한 문제를 해결하기 위해서는 유속 측정시 전자파 출력을 기존의 시스템보다 높게 물표면에 발사하여야 하며 안테나를 포함한 RF 모듈의 수신감도 및 지향성이 개선되어야 한다. 이에 편각측정이 가능하도록 이러한 사항에 주안점을 두어 새로운 시스템을 구성하였다. 수신감도 향상을 위해서는 물표면에 반사되어 돌아오는 신호를 가장 먼저 수신하는 안테나의 특성이 중요하며 그 다음 수신용 증폭기, IF 증폭기 순으로 개선이 필요하다. 본 연구에서는 안테나의 형태를 기존 파라볼릭 안테나에서 위상 배열 평면안테나로 변경하였으며, 이에 따른 이점으로는 송수신부를 분리하여 하나의 평면에 두 개의 안테나를 구성할 수 있다는 사항이다. 즉 외형적으로는 하나의 안테나로 보이지만 두 개의 안테나가 하나로 구성된 것이다. 송수신부를 분리하는 형태는 기존 파라볼릭 안테나에선 불가능한 구조로 변경에 따른 수신감도 향상은 수치적으로 10dB 이상 개선하였다. 송수신부 분리가 수신감도에 영향을 미치는 이유는 물표면으로 발사된 송신 신호의 일부가 수신단으로 유입되는 현상으로 누설되는 송신 신호를 최대한 차단하는 분리도가 수신 신호 검출에 직접적인 양향을 주기 때문에다. 평면 안테나를 적용하면 기존 파라볼릭 안테나에서 사용하던 써큘레이터라는 부품을 삭제할 수 있으며, 안테나의 구조적인 분리를 통해서 수신감도를 개선할 수 있었다. 안테나의 지향성은 발사하는 전자파의 빔폭 성능과 일치하며 각도 단위로 표시한다. 각도 값이 작을수록 전자파의 에너지가 한 곳에 집중된다고 말할 수 있다. 즉 빔폭이 크면 측정시 반사면적이 커져 정확한 지점의 유속을 측정하기 어려운 문제가 발생한다. 본 연구를 통해 빔폭은 기존 안테나 대비2도를 개선하였으며 25%의 개선 효과를 얻었다. 또한 수신감도 및 지향성 개선과 더불어 전자파의 출력을 기존 장비 대비하여 1.6배를 증가하여 편각측정을 위한 전자파표면 유속계의 성능을 개선하였다.