• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.281-284
• /
• 2019

본 논문은 CNN (Convolution Neural Networks)의 첫 번째 컨볼루션층(convolution layer)을 RGB-csb(RGB channel separation block)로 대체하여 입력 영상의 RGB 값을 특징 맵에 적용시켜 정확성을 제고시킬 수 있는 선행연구 결과에 추가적으로, 훈련 및 시험 영상 수에 따른 분석을 통하여 정확도 향상방법을 제안한다. 제안한 방법은 영상의 개수가 작을수록 각 학습 간의 정확도 편차가 크게 나타나는 불안정성은 있지만 기존 CNN모델에 비하여 정확도 차이가 증가함을 알 수 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.11a
• /
• pp.46-49
• /
• 2012

본 논문에서는 3차원 입체 비디오처리 기술의 최종목표인 디지털 홀로그램을 생성하는데 필요한 객체의 좌표와 색상정보가 들어있는 같은 시점과 해상도인 RGB 영상과 깊이 영상을 획득하여 가상 시점의 디지털 홀로그램을 생성하는 시스템을 제안한다. 먼저, 가시광선과 적외선의 파장을 이용하여 파장에 따라 투과율이 달라지는 콜드 미러를 사용하여 각각의 시점이 같은 다시점 RGB와 깊이 영상을 얻는다. 카메라 시스템이 갖는 다양한 렌즈 왜곡을 없애기 위한 보정 과정을 거친 후에 해상도가 서로 틀린 RGB 영상과 깊이 영상의 해상도를 같게 조절한다. 그 다음, DIBR(Depth Image Based Rendering) 알고리즘을 이용하여 원하는 가상 시점의 깊이 정보와 RGB 영상을 생성한다. 그리고 깊이 정보를 이용하여 디지털 홀로그램으로 구현할 객체만을 추출한다. 마지막으로 컴퓨터 생성 홀로그램 (computer-generated hologram, CGH) 알고리즘을 이용하여 추출한 가상 시점의 객체를 디지털 홀로그램으로 변환한다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.4
• /
• pp.136-150
• /
• 2022

In this study, a comparative review was conducted on how to use RGB images to obtain river topographic information, which is one of the most essential data for eco-friendly river management and flood level analysis. In terms of the topographic information of river zone, to obtain the topographic information of flow section is one of the difficult topic, therefore, this study focused on estimating the river topographic information of flow section through RGB images. For this study, the river topography surveying was directly conducted using ADCP and RTK-GPS, and at the same time, and orthomosiac image were created using high-resolution images obtained by drone photography. And then, the existing developed regression equations were applied to the result of channel topography surveying by ADCP and the band values of the RGB images, and the channel bathymetry in the study area was estimated using the regression equation that showed the best predictability. In addition, CCHE2D flow modeling was simulated to perform comparative verification of the topographical informations. The modeling result with the image-based topographical information provided better water depth and current velocity simulation results, when it compared to the directly measured topographical information for which measurement of the sub-section was not performed. It is concluded that river topographic information could be obtained from RGB images, and if additional research was conducted, it could be used as a method of obtaining efficient river topographic information for river management.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.3
• /
• pp.61-71
• /
• 2018

When triangular meshes are generated from the point clouds in global space reconstructed through camera pose estimation against captured RGB-D streams, the quality of the resulting meshes improves as more triangles are hired. However, for 3D reconstructed models beyond some size threshold, they become to suffer from the ugly-looking artefacts due to the insufficient precision of RGB-D sensors as well as significant burdens in memory requirement and rendering cost. In this paper, for the generation of 3D models appropriate for real-time applications, we propose an effective technique that extracts high-quality textures for moderate-sized meshes from the captured colors associated with the reconstructed point sets. In particular, we show that via a simple method based on the mapping between the 3D global space resulting from the camera pose estimation and the 2D texture space, textures can be generated effectively for the 3D models reconstructed from captured RGB-D image streams.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.13 no.2
• /
• pp.163-168
• /
• 1995

There are four types of color model to repesent color, which are RGB, IHS, CMY, and YIQ color model. RGB color model is the designation of the digital numbers(DNs) of the three primary colors(red, green, and blue), which are used to produce color images on color monitors. IHS color model is the designation of in-tensity, hue, and saturation(IHS). An advantage of considering color in terms of IHS over that of RGB is arrives more easily at a desired color product mathematically. In this study, authors use the IHS transformation and in-tensity-adjustment method to produce the color map images with Landsat TM and scanned map image. And, authors suggest the problems and their solutions when users produce the desired new images with satellite images and map images.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.277-277
• /
• 2021

합류부는 인공수로 또는 자연하천에서 흔히 존재하며 매우 복잡한 흐름 구조가 발생하는 곳이다. 특히 본류와 지류의 유속장의 차이에 따라 발생하는 전단층은 흐름과 물질이 혼합되는 경계면이 되며, 흐름 구조가 전단층을 따라 발달한다는 특징으로 인해 수리학적으로 매우 중요하다. 최근 원격탐사 기법의 발전에 따라 위성이나 드론과 같은 무인 이동체를 이용한 하천 계측법이 수질 및 지형변화 연구들에 광범위하게 적용되고 있다. 그 중 RGB 항공영상은 해상도가 높고 취득 비용이 저렴하여 확장성 및 활용도가 높다. 본 연구에서는 합류부 전단층이 촬영된 RGB 항공 영상을 이용해 합류부 전단층 분석에 활용하는 방법을 제안한다. 제안되는 방법은 RGB 항공 영상에서 본류와 지류의 수체 영역을 각각 추출하기 위해 가우시안 혼합 모형(Gaussian mixture model)을 이용한다. 추출된 수체 영역에는 자기조직화지도(self-organizing map)을 적용하고 좌표 변환을 하여 정량적인 특징을 추출한다. 본 연구에서는 알고리듬의 적용 예로서 구글어스를 통해 확보된 낙동강-남강 합류부의 항공 영상을 분석한다. 본 추출법을 이용하면 접촉식 센서를 이용하는 기존의 전단층 계측 방법들에 비해 경제적이고 안전하며 합류부 흐름의 평면적 분석을 가능하게 할 수 있을 것으로 기대된다.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.340-348
• /
• 2021

Continuous monitoring of RGB (Red, Green, Blue) vegetation indices is important to apply remote sensing technology for the estimation of crop growth. In this study, we evaluated the performance of eight vegetation indices derived from soybean RGB images with various agronomic parameters under drought stress condition. Drought stress influenced the behavior of various RGB vegetation indices related soybean canopy architecture and leaf color. In particular, reported vegetation indices such as ExGR (Excessive green index minus excess red index), Ipca (Principal Component Analysis Index), NGRDI (Normalized Green Red Difference Index), VARI (Visible Atmospherically Resistance Index), SAVI (Soil Adjusted Vegetation Index) were effective tools in obtaining canopy coverage and leaf chlorophyll content in soybean field. In addition, the RGB vegetation indices related to leaf color responded more sensitively to drought stress than those related to canopy coverage. The PLS-DA (Partial Squares-Discriminant Analysis) results showed that the separation of RGB vegetation indices was distinct by drought stress. The results, yet preliminary, display the potential of applying vegetation indices based on RGB images as a tool for monitoring crop environmental stress.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.46-51
• /
• 2020

Pine wilt disease is one of the reasons that results in huge damage on pine trees in east Asia including Korea, Japan, and China, and early finding and removing the diseased trees is an efficient way to prevent the forest from wide spreading. This paper proposes a searching method of the damaged pine trees from wilt disease in ortho-images corrected from RGB images, which are captured by unmanned aviation vehicles. The proposed method constructs patch-based classifier using ResNet18 backbone network, classifies the RGB ortho-image patches, and make the results as a heat map. The heat map can be used to find the distribution of diseased pine trees, to show the trend of spreading disease, and to extract the RGB distribution of the diseased areas in the image. The classifier in the work shows 94.7% of accuracy.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.2
• /
• pp.155-160
• /
• 2014

In this paper, an algorithm using RGB-depth camera is proposed to detect smoke in interrior. RGB-depth camera, the Kinect provides RGB color image and depth information. The Kinect sensor consists of an infra-red laser emitter, infra-red camera and an RGB camera. A specific pattern of speckles radiated from the laser source is projected onto the scene. This pattern is captured by the infra-red camera and is analyzed to get depth information. The distance of each speckle of the specific pattern is measured and the depth of object is estimated. As the depth of object is highly changed, the depth of object plain can not be determined by the Kinect. The depth of smoke can not be determined too because the density of smoke is changed with constant frequency and intensity of infra-red image is varied between each pixels. In this paper, a smoke detection algorithm using characteristics of the Kinect is proposed. The region that the depth information is not determined sets the candidate region of smoke. If the intensity of the candidate region of color image is larger than a threshold, the region is confirmed as smoke region. As results of simulations, it is shown that the proposed method is effective to detect smoke in interior.

• Journal of Korea Society of Industrial Information Systems
• /
• v.10 no.2
• /
• pp.102-108
• /
• 2005

CIELAB coordinate is represented by one lightness component and two chromaticity components and similar to human visual system. Visual devices such as computer monitor display images using RGB coordinate. We propose a technique for inserting the watermark of visually recognizable mark into the middle frequency domain of image. RGB coordinate image is transformed into CIELAB coordinate, which include the characteristics of Human vision and then a* component is transformed into DFT(Discrete Fourier transform) transform.