• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.301-306
• /
• 2004

이 논문에서는 1m 해상도 위성영상에서 관측할 수 있는 여러 인공지물 중에서 아파트 및 산업용 건물 등, 비교적 중대형이고 사각형 형태인 건물들을 반자동으로 추출하기 위한 알고리즘을 소개한다. 기존에 연구된 건물추출을 위한 방식으로는 Perceptual Grouping, 스테레오 분석, LIDAR 센서 등에서 얻은 3 차원 정보를 이용하는 방식 등이 있다. 여기서는 단일영상 만을 이용하여 반자동으로 건물을 추출하는 알고리즘을 제안한다 이 알고리즘은 먼저 영상으로부터 라인을 추출한 후, 라인분석을 통하여 건물의 위치와 방향을 결정하고, 탬플릿 정합을 이용하여 이를 개선한다. 그리고 자동으로 추출된 건물외각선에 포함된 오류를 제거하기 위하여 수동편집 단계를 수행한다. 또한 먼저 수행한 건물추출 결과를 활용하여 주변에 유사한 형태의 건물외각선을 빠르게 추출하기 위해 기존에 추출된 건물 외각선 Polygon 을 탬플릿으로 정의하고 정합을 수행하여 건물 외각선을 추출한다. 개발된 알고리즘은 기존의 다른 방식들에 비해 추가적인 영상이나 정보를 요구하지 않고도 빠른 시간에 정확한 사각형형태의 건물을 추출할 수 있었다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.21 no.1
• /
• pp.19-26
• /
• 2003

As recently, high-resolution satellite images of 1m spatial resolution are opened to the public and able to be used commercially, the studies that make ortho-images using them and apply to digital mapping and database of geo-spatial information system are having been progressed actively. Therefore, the purposes of this study are to establish the auto-extraction methods and to develope algorithms for automatically extracting buildings out of man-made structures, after making the IKONOS ortho-image. As the result of this study, we can extract buildings automatically at 72% out of the whole buildings. And we have analyzed the error trend by means of the comparison with ortho-image, digital map and drawing result, then we could know that obtain the good result for extraction of the building through the methods and algorithms of this study.

• Korean Journal of Remote Sensing
• /
• v.29 no.5
• /
• pp.499-508
• /
• 2013

This article presents a new method for semi-automatic extraction of building information (height, shape, and footprint location) from monoscopic urban scenes. The proposed method is to expand Semi-automatic Volumetric Shadow Analysis (SVSA), which can handle occluded building footprints or shadows semi-automatically. SVSA can extract wrong building information from a single high resolution satellite image because SVSA is influenced by extracted shadow area, image noise and objects around a building. The proposed method can reduce the disadvantage of SVSA by using multi-spectral images. The proposed method applies SVSA to panchromatic and multi-spectral images. Results of SVSA are used as parameters of a cost function. A building height with maximum value of the cost function is determined as actual building height. For performance evaluation, building heights extracted by SVSA and the proposed method from Kompsat-2 images were compared with reference heights extracted from stereo IKONOS. The result of performance evaluation shows the proposed method is a more accurate and stable method than SVSA.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.3 s.33
• /
• pp.59-67
• /
• 2005

Building information is primary source in many applications such as mapping, telecommunication, car navigation and virtual city modeling. While aerial CCD images which are captured by passive sensor(digital camera) provide horizontal positioning in high accuracy, it is far difficult to process them in automatic fashion due to their inherent properties such as perspective projection and occlusion. On the other hand, LIDAR system offers 3D information about each surface rapidly and accurately in the form of irregularly distributed point clouds. Contrary to the optical images, it is much difficult to obtain semantic information such as building boundary and object segmentation. Photogrammetry and LIDAR have their own major advantages and drawbacks for reconstructing earth surfaces. The purpose of this investigation is to automatically obtain spatial information of 3D buildings by fusing LIDAR data with aerial CCD image. The experimental results show that most of the complex buildings are efficiently extracted by the proposed method and signalize that fusing LIDAR data and aerial CCD image improves feasibility of the automatic detection and extraction of buildings in automatic fashion.

• Proceedings of the KSRS Conference
• /
• 2009.03a
• /
• pp.13-17
• /
• 2009

고해상도 위성영상의 분류 기술은 최근 가장 활발히 연구되고 있는 분야 중 하나로 텍스쳐(texture), NDVI, PCA 영상 등 다양한 전처리 정보들을 추출하고 이를 멀티스펙트럴 밴드와 조합하여 분류 정확도를 높이는 기술을 개발하는 연구들이 주를 이루고 있다. 고해상도 위성영상에서 건물의 그림자와 옆벽면의 폐색 지역은 개체 추출 및 분류를 방해하는 주된 요인이 되며, 다양한 형태와 분광특성을 갖는 개개의 건물은 자동 분류 과정을 통해 제대로 식별되지 않는다는 한계를 갖는다. 이에 본 연구에서는 KOMPSAT-2 단영상으로부터 효율적으로 건물 정보 및 토지피복을 분류하기 위하여, 추출된 건물 정보를 바탕으로 건물의 그림자와 폐색지역을 보정한 후 비건물 지역에 대한 분류를 수행하여 분류 정확도를 높이고자 하였다. 우선 삼각벡터구조 기반의 반자동 인터페이스를 이용하여 건물의 3차원 모델 및 그림자 영역을 추출하고 이로부터 추출된 그림자 영역을 효과적으로 보정하기 위해 반복 선형회귀 연산을 이용한 그림자 보정을 수행한 후 inpainting 기법을 건물 폐색영역 복원에 적용하여 영상의 품질을 향상시켰다. 이러한 과정을 통해 도심 지역의 영상 분석에 있어 가장 큰 오차를 일으키는 인공물의 그림자와 폐색에 의한 오차를 최소화한 후 분류에 적용하여 이를 보정 전 영상을 이용한 분류 결과와 비교하였다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.17 no.4
• /
• pp.421-429
• /
• 1999

It is estimated that, in the twenty-first century, 70％ of global citizens will live in urban areas. This accelerated urbanization will require a greater need for the building DEM and orthoimagery along with Geographic Information System for urban management. The building DEM requires the detection of outlines showing building shapes. To do this, automatic and semiautomatic building extractions are usually used. However, in cases where automatic extraction is performed directly from the aerial images, accurate building outline extraction is very difficult because of shadow, roof color, and neighboring trees making it hard to discern building roofs. To overcome this problem semiautomatic building extraction was suggested in this paper. When a roof texture was homogeneous, building outline detection was performed by mouse-clicking on a part of the roof. To construct the building outlines when the texture was not homogeneous, a computer program was developed to search out corner points by clicking spots near corner points. The building DEM was generated by taking into account building outlines and heights calculated by image matching.

• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.339-353
• /
• 2023

As the availability of high-resolution satellite imagery increases, improvement of positioning accuracy of satellite images is required. The importance of orthorectified images is also increasing, which removes relief displacement and establishes true localization of man-made structures. In this paper, we performed automated extraction of building rooftops and total building areas within original satellite images using the existing building height database. We relocated the rooftop sin their true position and generated an orthorectified building layer. The extracted total building areas were used to blank out building areas and generate true orthographic non-building layer. A final orthorectified image was provided by overlapping the building layer and non-building layer.We tested the proposed method with KOMPSAT-3 and KOMPSAT-3A satellite images and verified the results by overlapping with a digital topographical map. Test results showed that orthorectified building layers were generated with a position error of 0.4m.Through the proposed method, the feasibility of automated true orthoimage generation within dense urban areas was confirmed.

• Proceedings of the KSRS Conference
• /
• 2008.03a
• /
• pp.101-108
• /
• 2008

건물의 3차원 모델링은 3차원 공간정보를 구축하는데 있어서 매우 중요한 요소이다. 기존의 3차원 건물 모델링은 대부분 입체 항공사진을 이용하여 도화사에 의해 수동으로 진행되어 많은 시간과 비용이 소요된다. 이러한 한계를 극복하기 위한 방안으로 최근에는 항공라이다(LiDAR) 데이터를 이용한 모델링 방법에 대한 연구가 활발히 진행되고 있다. 기존의 항공라이다 데이터를 이용한 3차원 모델링 연구는 항공라이다 점 데이터를 보간 과정을 통하여 픽셀구조로 변환하거나 수치지도, 항공영상 등의 이종 데이터간의 융합을 통하여 건물을 모델링하는 방안 등을 제시하였다. 본 논문은 기존 건물 모델링 기법에서 사용되었던 점 데이터의 픽셀구조로의 변환 및 이종 데이터간의 융합 등의 방법을 배제하고 항공라이다 데이터만을 이용한 건물의 자동 모델링 방법을 제안하였다. 건물지붕에 대한 항공라이다 데이터를 3차원 공간상에서 재귀적으로 분할하여 패치(patch)를 구성하고, 동일한 속성을 갖는 패치들을 병합하여 건물의 구성요소를 추출한다. 추출되어진 건물의 구성요소를 대표하는 모델을 생성하여 전체적인 건물의 3차원 모델을 구성한다. 항공라이다 데이터를 이용하여 제안된 방법으로 실험한 결과, 다양한 형태의 건물 모델을 자동으로 구성할 수 있었다.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1067-1087
• /
• 2018

In a study for LiDAR data based building boundary extraction, usually dense point cloud was used to cluster building rooftop area and extract building outline. However, when we used DSM generated from stereo image matching to extract building boundary, it is not trivial to cluster building roof top area automatically due to outliers and large holes of point cloud. Thus, we propose a technique to extract building boundary semi-automatically from the DSM created from stereo images. The technique consists of watershed segmentation for using user input as markers and recursive MBR algorithm. Since the proposed method only inputs simple marker information that represents building areas within the DSM, it can create building boundary efficiently by minimizing user input.

• Journal of Korean Society for Geospatial Information Science
• /
• v.11 no.1 s.24
• /
• pp.29-37
• /
• 2003

The High-resolution satellite images are able to get the latest information of wide range area and to shorten updating cycle of digital map better than the aerial images. Especially, as high-resolution satellite images are opened to public recently and able to be used commercially, the studies that make ortho-images using them and apply to the digital mapping and the database of geo-spatial information system are having been progressed actively. Therefore, the purposes of this study are to establish the auto-extraction methods and to develop algorithms for automatically extracting buildings which are distributed very much in urban areas and which updating cycle needs to shorten, out of man-made structures in the IKONOS ortho-image with 1m spatial resolution. The result of this study, we can extract automatically extract 72% out of the whole buildings. And we could know that the methods and algorithms proposed in this study are good relatively analyzing the error trend by means of the comparison with ortho-image, digital map and hawing result.