• 전자공학회논문지CI
• /
• 제45권5호
• /
• pp.56-62
• /
• 2008

의사결정나무를 구성하여 강판튜브 비파괴평가에 사용하는 산업용 CR영상의 측정 패턴인식을 도모한다. 본래 비파괴평가는 기계학습기법에 의한 패턴식별과 그 분류에 적합한 분야이다. 의사결정나무의 속성들은 비파괴평가 테스트 절차로부터 취한다. 방사선조사 입사각, 경사도 및 거리 둥의 기하학적 특성들은 입력 영상 데이터 분석으로부터 추정한다. 이 요소들은 대상 입력을 의사결정나무에서 미리 정해진 분류에로 정확히 그리고 쉽게 분류가 이루어지도록 한다. 이 알고리즘은 비파괴평가 결과의 특성화를 간단히 하며 특성 결정을 간편하게 한다. 실험 결과는 제안한 알고리즘의 유용성을 보였다.

• 전기전자학회논문지
• /
• 제20권3호
• /
• pp.226-234
• /
• 2016

전기 저항 단층촬영법(ERT)은 대상체 내부 단면의 저항률 분포를 추정하고 이를 영상화하는 기술이다. ERT의 영상복원은 매우 비정치성이 강한 역문제의 일종으로 의미있는 영상을 얻기 위해서는 조정기법이 사용된다. 대표적으로 l2-norm 조정기법, l1-norm 조정기법, Total Variation 조정기법이 사용되며, 조정기법에 따라 ERT의 영상복원 성능이 달라진다. 즉, 상황에 맞는 적절한 조정기법의 사용은 ERT 영상 복원을 개선할 수 있다. 따라서, 본 논문에서는 모의실험을 통하여 상황에 따른 세 가지 조정기법의 영상복원 성능을 비교하였다.

• 한국컴퓨터정보학회논문지
• /
• 제13권2호
• /
• pp.235-242
• /
• 2008

이동자율로봇은 작업 공간을 벗어난 작업에 대하여 높은 성능을 보일 수 있으므로 고정 베이스 구조인 매니플레이터에 비하여 다양한 작업 환경에서 유용하다. 임의의 위치에 있는 물체를 인식하기 위하여 이동자율로봇에 부착된 2자유도의 능동카메라에 의해 입력되는 영상과 능동카메라의 기구학적 관계와 직각좌표계를 이용하여 물체의 위치와 이동로봇의 위치를 구하는 방법을 제시한다. 동차행렬을 이용하여 이미지정보와 물체의 위치를 해석하므로 이동자율로봇의 최적경로를 생성한다. 최종적으로, 물체의 인식을 통하여 이동로봇을 제어할 수 있는 조인트변수의 값을 계산한다. 제안된 방법은 제작된 이동자율로봇의 시뮬레이션과 실험을 통하여 확인되어지고 논의된다.

• 대한원격탐사학회지
• /
• 제8권2호
• /
• pp.131-145
• /
• 1992

A low cost personal computer and image processing S/W were empolyed to derive Digtal Elevation Model(DEM) of tidal flat from multitemporal LANDSAT TM images, and to create three-dimensional(3D) perspective views of the tidel flat on Komso bay in west coasts of Korea. The method for generation of Digital Elevation Model(DEM) in tidal flat was considered by overlapping techniques of multitemporal LANDSAT TM images and interpolations. The boundary maps of tidal flat extracted from multitemporal images with different water high were digitally combined in x, y, z space with tide in formation and used as an inputcontour data to obtain an elevation model by interpolation using spline function. Elevation errors of less than $\pm$0.1m were achived using overlapping techniques and a spline interpolation approach, respectively. The derived DEM allows for the generation of a perspective grid and drape on the satellite image values to create a realistic terrain visualization model so that the tidal flat may be viewed from and desired direction. As the result of this study, we obtained elevation model of tidal flats which contribute to characterize of topography and monitoring of morphological evolution of tidal flats. Moreover, the modal generated here can be used for simulation of innudation according to tide and support other studies as a supplementary data set.

• 상하수도학회지
• /
• 제32권6호
• /
• pp.573-581
• /
• 2018

The purpose of this study is to evaluate the fixed wing type domestic UAV for monitoring of algae bloom in aquatic environment. The UAV used in this study is operated automatically in-flight using an automatic navigation device, and flies along a path targeting preconfigured GPS coordinates of desired measurement sites input by a flight path controller. The sensors used in this study were Sequoia multi-spectral cameras. The photographed images were processed using orthomosaics, georeferenced digital surface models, and 3D mapping software such as Pix4D. In this study, NDVI(Normalized distribution vegetation index) was used for estimating the concentration of chlorophyll-a in river. Based on the NDVI analysis, the distribution areas of chlorophyll-a could be analyzed. The UAV image was compared with a airborne image at a similar time and place. UAV images were found to be effective for monitoring of chlorophyll-a in river.

• Journal of Multimedia Information System
• /
• 제8권4호
• /
• pp.203-210
• /
• 2021

Deep leaning convolutional neural networks (CNN) have successfully been applied to image super-resolution (SR). Despite their great performances, SR techniques tend to focus on a certain upscale factor when training a particular model. Algorithms for single model multi-scale networks can easily be constructed if images are upscaled prior to input, but sub-pixel convolution upsampling works differently for each scale factor. Recent SR methods employ multi-scale and multi-path learning as a solution. However, this causes unshared parameters and unbalanced parameter distribution across various scale factors. We present a multi-scale single-path upsample module as a solution by exploiting the advantages of sub-pixel convolution and interpolation algorithms. The proposed model employs sub-pixel convolution for the highest scale factor among the learning upscale factors, and then utilize 1-dimension interpolation, compressing the learned features on the channel axis to match the desired output image size. Experiments are performed for the single-path upsample module, and compared to the multi-path upsample module. Based on the experimental results, the proposed algorithm reduces the upsample module's parameters by 24% and presents slightly to better performance compared to the previous algorithm.

• Applied Microscopy
• /
• 제50권
• /
• pp.23.1-23.9
• /
• 2020

We propose an effective deep learning model to denoise scanning transmission electron microscopy (STEM) image series, named Noise2Atom, to map images from a source domain 𝓢 to a target domain 𝓒, where 𝓢 is for our noisy experimental dataset, and 𝓒 is for the desired clear atomic images. Noise2Atom uses two external networks to apply additional constraints from the domain knowledge. This model requires no signal prior, no noise model estimation, and no paired training images. The only assumption is that the inputs are acquired with identical experimental configurations. To evaluate the restoration performance of our model, as it is impossible to obtain ground truth for our experimental dataset, we propose consecutive structural similarity (CSS) for image quality assessment, based on the fact that the structures remain much the same as the previous frame(s) within small scan intervals. We demonstrate the superiority of our model by providing evaluation in terms of CSS and visual quality on different experimental datasets.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2002년도 Proceedings of the International Welding/Joining Conference-Korea
• /
• pp.314-319
• /
• 2002

The Automation and Control Group at the University of Brasilia is developing an automatic welding station based on an industrial robot and a controllable welding machine. Several techniques were applied in order to improve the quality of the welding joints. This paper deals with the implementation of a laser-based computer vision system to guide the robotic manipulator during the welding process. Currently the robot is taught to follow a prescribed trajectory which is recorded a repeated over and over relying on the repeatability specification from the robot manufacturer. The objective of the computer vision system is monitoring the actual trajectory followed by the welding torch and to evaluate deviations from the desired trajectory. The position errors then being transfer to a control algorithm in order to actuate the robotic manipulator and cancel the trajectory errors. The computer vision systems consists of a CCD camera attached to the welding torch, a laser emitting diode circuit, a PC computer-based frame grabber card, and a computer vision algorithm. The laser circuit establishes a sharp luminous reference line which images are captured through the video camera. The raw image data is then digitized and stored in the frame grabber card for further processing using specifically written algorithms. These image-processing algorithms give the actual welding path, the relative position between the pieces and the required corrections. Two case studies are considered: the first is the joining of two flat metal pieces; and the second is concerned with joining a cylindrical-shape piece to a flat surface. An implementation of this computer vision system using parallel computer processing is being studied.

• Ocean Systems Engineering
• /
• 제13권2호
• /
• pp.195-224
• /
• 2023

This paper proposes a method for the acoustic imaging wherein the traditional requirement of the relative movement between the transmitter and target is overcome. This is facilitated through the beamforming acoustic array in the transmitter, in which the target is illuminated by the array at various azimuth and elevation angles without the physical movement of the acoustic array. The concept of beam steering of the acoustic array facilitates the formation of the beam at desired angular positions of azimuth and elevation angles. This paper substantiates that the combination of illumination of the target from different azimuth and elevation angles with respect to the transmitter (through the beam steering of beam forming acoustic array) and the beam steering at multiple frequencies (through SF) results in enhanced reconstruction of images of the target in the underwater scenario. This paper also demonstrates the possibility of reconstruction of the image of a target in underwater without invoking the traditional algorithms of Digital Image Processing (DIP). This paper comprehensively and succinctly presents all the empirical formulae required for modelling the acoustic medium and the target to facilitate the reader with a comprehensive summary document incorporating the various parameters of multi-disciplinary nature.

• Current Optics and Photonics
• /
• 제8권3호
• /
• pp.259-269
• /
• 2024

Optical imaging systems that operate through atmospheric pathways often suffer from image degradation, mainly caused by the distortion of light waves due to turbulence in the atmosphere. Adaptive optics technology can be used to correct the image distortion caused by atmospheric disturbances. However, there are challenges in conducting experiments with strong atmospheric conditions. An optical phase plate (OPP) is a device that can simulate real atmospheric conditions in a lab setting. We suggest a novel two-step process to fabricate an OPP capable of simulating the effects of atmospheric turbulence. The proposed fabrication method simplifies the process by eliminating additional activities such as phase-screen design and phase simulation. This enables an efficient and economical fabrication of the OPP. We conducted our analysis using the statistical fluctuations of the refractive index and applied modal expansion using Kolmogorov's theory. The experiment aims to fabricate an OPP with parameters D/r₀ ≈ 30 and r₀ ≈ 5 cm. The objective is defined with the strong atmospheric conditions. Finally, we have fabricated an OPP that satisfied the desired objectives. The OPP closely simulate turbulence to real atmospheric conditions.