• Tunnel and Underground Space
• /
• v.8 no.4
• /
• pp.342-350
• /
• 1998

In this study, fracture network in rock mass was interpreted using borehole wall images obtained by televiewer. The orientation and JRC value of major joint set were evaluated adopting image analysis techniques, of which process were written in macro-program code. As linking JRC to joint stiffness using Barton-Bandis model, fracture network map was produced for application to jointed rock modelling in numerical analysis of underground structure.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.3
• /
• pp.243-253
• /
• 2002

These days, the application range of digital photogrammetry is being extended actively, so the great variety of research is being progressed about improvement of measurement accuracy. This method can acquisite a high analysis accuracy and can acquisite easily image. But, So this method require a much processing time and effort by increasing a data amount, as the automation of processing must be completed for efficiency improvement of processing. In this study, the automation of image processing stage is established for multi-image aquisition and analysis about a radio telescope. Also, the precise measurement and the accuracy on object were intended to be improved. As a result of this study, the accuracy on the object which demands precise measurement was enhanced from multi image analysis, and also the assembly accuracy of the object could be checked by precise measurement and curve fitting.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.1
• /
• pp.41-50
• /
• 2020

The National Geographic Information Institute of Korea takes digital aerial photograph images every two years to make and modify/renew the digital map. The cameras for aerial photogrammetry to capture these digital aerial photographs are divided into frame types and line types. Computer vision analysis of aerial photograph images was only possible for frame type. Thus, in this study, Line type aerial photograph images was intended to generate geospatial information through computer vision analysis, and forest geospatial information was created as a method for the utilization of aerial picture images. As a result, geospatial information generated by computer vision analysis of line type aerial photograph images showed that RMSE of horizontal and vertical position errors was less than quadruple that of GSD. Forest geospatial information was generated using geospatial information generated by computer vision analysis. It was confirmed that extraction of the crown of tree and calculation of tree height are possible. Through this study, it is expected that utilization of aerial photograph images will be improved.

• The KIPS Transactions:PartB
• /
• v.8B no.4
• /
• pp.389-394
• /
• 2001

본 논문에서는 독립 성분 해석(Independent Component Analysis, ICA) 기법과 인근 평균 및 정규화를 이용한 영상 분류 방법을 제안하였다. ICA에 잡음을 주어 영상을 분류하였을 때, 잡음에 대한 강인성을 증가시키기 위하여, 제안된 인근 평균 및 정규화를 전처리로 적용하였다. 제안된 방법은 전처리 없이 ICA에 주성분 해석(Principal Component Analysis, PCA)을 이용한 것에 비해 잡음에 대한 강인성을 증가시키는 것을 모의 실험을 통하여 확인하였다.

• Aerospace Engineering and Technology
• /
• v.13 no.2
• /
• pp.99-107
• /
• 2014

There are two types of Physical Model and RFM (Rational Function Model) is to determinate ground coordinates using KOMPSAT-2 and KOMPSAT-3 satellite data. Generally, RPCs(Rational Polynomial Coefficients) based on RFM is provided for users. This RPCs is to compute the ground coordinates to the image coordinates. If users produce ortho-image with provided RPCs is useful, directly compute the ground coordinates corresponding to image coordinates and check location accuracy etc. are difficult. In this study, a basic algorithm of inverse RPCs that calculates the image coordinates to ground coordinates, compute based on provided RPCs and evaluation of determinated ground coordinates using developed inverse RPCs were proposed.

• Journal of Korean Society for Geospatial Information Science
• /
• v.2 no.2 s.4
• /
• pp.131-142
• /
• 1994

Generally, there are two methods which generates the base map of Geo-Spatial Information System(GSIS). one is the digitizing of existing map, and the other is the analytical plotting method editing data acquired by sensors using computers. But the analytical plotting method and method of the digitizing of existing map is technically complex and has the disadvantages in the costs and time. The subject region of study(the Kwangyang province), was photographed by aircraft, and photographing scale was 1/6,000. Then this area was divided into two specific regions, the residential area, and the agricultural area. In this study, we developed the algorithm that generated base map of database in GSIS from the aerial photo. This algorithm is as followed. First, the digital aerial photos were generated using these aerial photos. Second, these digital aerial photos were enhanced by implementing the histogram equalization. Third, the objects of the enhanced images were extracted by implementing thresholding and edged detection techiques of image segmentation. Finally, these images could be used to updated the base map of database in GSIS. The result obtained from this study showed that method used by this study were more efficient than existing method in costs and time.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.328-335
• /
• 2007

Ontology is represented by the shared concepts and relations among those. Many studies have been actively working on sharing human's knowledge with that of systems by using it. For a typical example, there is the design and implementation of ontology system for image understanding. However conventional studies on ontology-based image understanding have proposed not concrete methods but conceptual idea. In this paper, we propose an ontology-based image understanding system with following four processes: i)knowledge representation of a specific domain by the ontology, ii)feature extraction of objects through image processing and image analysis, iii)image interpretation by object features, and iv)reduction of ambiguity existing in image interpretation by ontology reasoning. We implement an image understanding system based on the proposed processed, and show the effectiveness of the proposed system from experimental results in a specific domain.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.145-150
• /
• 2003

고해상도 위성영상을 이용한 산림의 분석은 기존의 중ㆍ저해상도 영상의 분석과 다른 접근이 필요하다. 본 연구는 임분 특성을 해석하는데 중요한 판독기준인 texture를 이용하여 영상 안에서 임상, 임목직경급, 수관울폐도 등에 따른 Texture 정보를 비교 분석하고자 한다. 울산 일부 산림지역을 대상으로 3개의 가시광선 밴드와 1개의 근적외선 밴드의 1m IKONOS 영상을 이용하여 Texture 정보를 추출하는데 일반적으로 사용되는 통계적인 방법 중에 하나인 GLCM(Gray-Level Co-occurrence matrix)을 통해 Texture 분석을 하였다. 또한 1996년도에 제작된 4차 임상도를 통해 추출된 산림 특성별 Texture 정보를 비교 검토하여 고해상도 위성영상을 활용하여 산림 특성을 해석하는데 최적의 Texture 정보를 제시하고자 하였다. 고해상도 영상에서 나타나는 임분의 특성별 질감정보는 임상, 직경, 임목밀도에 따라 다양하게 나타났다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.18 no.1
• /
• pp.25-32
• /
• 2000

These days, the quantitative analysis of digital image by on-line image analysis system is being progressed actively, so the application of digital image is being groped in the safe test of construction. In this study, the synchronized 3D image acquisition and the system for processing that were established for analyzing the deflection of construction by using the acquired image from CCD camera. The reliability and the possibility of this established system are presented by deriving the accuracy of image analysis and the deflection of object through concrete loading test.

• Proceedings of the KSRS Conference
• /
• 2000.04a
• /
• pp.178-182
• /
• 2000

본 연구의 목적은 실험실에서 퇴적물의 다분광반사 특성과 물성을 측정하고 이를 위성 영상에 적용하여 영상에서 나타나는 퇴적물의 분광차이의 원인을 해석하고, 위성영상에서의 퇴적물의 분류 가능성을 연구하는데 있다. 연구에서는 Landsat TM위성 영상과 350~2500nm 파장대역에 대한 퇴적물 시료의 분광측정 자료를 사용하였으며, 기존의 조사 자료를 토대로 TM 영상에서 퇴적물을 분류한 후, 현장에서 시료를 채취하여 입도 분류를 실시하였다. 퇴적물의 입도와 함수비에 따른 분광특성변화를 검증하였으며, 입도와 함수비에 대한 회귀식을 구하여 이를 영상에 적용 분류하였다. 분석 결과 다분광자료 측정시 퇴적물입도에 따른 분광차이는 미약하였으며 이를 TM 자료로 재구성하였을 때는 분광특성을 구분할 수 없었다. 퇴적물의 분류는 TM Band 4, 5, 7을 이용한 회귀식을 적용할 때 비교적 정확하게 나타났으나, 영상에서 퇴적물의 분광 차이는 입도 크기가 직접적인 요인이 아니라 입도에 의한 함수비 및 유기물 함량의 차이에 기인한 것으로 해석된다.