• 대한전기학회논문지:시스템및제어부문D
• /
• 제49권12호
• /
• pp.659-666
• /
• 2000

A stereo matching has been an important tool for reconstructing three dimensional terrain. By using stereo matching technique, DEM(Digital Elevaton Map) can be generated by the disparity from a reference image to a target image. Generally disparity map can be evaluated by matching the reference image to the target image and if the role of the reference and the target are interchanged, a different DEM can be obtained. In this paper, we propose a new fusion technique to estimate the optimal DEM by eliminating the false DEM due to occlusion. To detect the false DEM, we utilize two measure of accuracy: self-consistency and cross-correlation score. We test the effectiveness of the proposed methods with a quantitative analysis using simulated images. Experimental result indicate that the proposed methods show 24.4% and 33.1% improvement over either DEM.

• 지적과 국토정보
• /
• 제44권1호
• /
• pp.127-138
• /
• 2014

수치지도의 도로 데이터를 효율적으로 갱신하기 위해서는 최신 갱신된 지도자료로부터 갱신된 정보만을 추출하여 반영하는 것이 효율적이다. 본 연구에서는 갱신 대상이 되는 네트워크 데이터와 갱신 참조 데이터를 중첩한 후 네트워크 매칭기법을 적용하여 갱신 대상 객체를 탐색한 후, 해당 대상 객체의 갱신 케이스를 분류하고 케이스에 따라 갱신하는 일련의 프로세스를 개발, 적용하고자 하였다. 이를 위해 수치지형도 도로중심선 데이터를 갱신 대상으로 하고 도로중심선 전자지도의 도로구간 데이터를 갱신 참조 데이터로 하여 버퍼 기반 네트워크 매칭 기법을 적용한 후, 각 객체의 중첩길이비를 계산하여 매칭 및 갱신 케이스에 따라 객체그룹을 분류하였으며 분류된 객체그룹에 갱신 프로세스를 적용하여 갱신된 수치지형도 도로중심선 데이터를 도출하였다. 적용 결과, 이종의 데이터로부터 갱신정보를 추출하여 도로 네트워크 데이터의 갱신과정에 이를 활용할 수 있을 것으로 판단된다.

• 대한공간정보학회지
• /
• 제20권3호
• /
• pp.101-108
• /
• 2012

수치지도는 국가에서 시행하고 있는 도로명주소를 포함 하지 못하고 있으며, 타 기관에서 직접 활용하기에는 문제점이 있어 연계 구축이 필요하나, 기 구축된 수치지도와 도로명 주소의 양이 방대하여 매칭을 수작업으로 진행할 경우 많은 예산 및 시간이 필요한 실정이다. 본 연구는 공간매칭을 이용하여 수치지도와 도로명주소의 자료 연계를 통하여 속성정보를 생성 하는 시스템을 개발하고, 이에 대한 매칭률을 분석하고자 한다. 대상지역에 대한 매칭율을 분석한 결과 수원시는 1:1000수치지도에서 건물이 84%, 도로가 67%로 좋은 매칭율을 나타냈고, 서귀포시는 건물 18%, 도로 21%로 나타났다.

• 대한공간정보학회지
• /
• 제3권2호
• /
• pp.213-220
• /
• 1995

차량 항법 시스템에서 맵 매칭(map matching) 방법은 데드 레코닝(dead reckoning) 기법으로 구한 차량의 위치가 지도상의 도로위에 일치하지 않는 경우에 이를 도로위에 매칭(matching) 시키기 위한 방법이다. 본 논문에서는 교차로 부근에서 차량의 회전을 감지함으로서 센서 및 수치지도자료에 기인하는 위치오류를 보정할 수 있는 새로운 맵 매칭 알고리즘을 제안하였다. 제안된 알고리즘은 진행거리의 상대오차와 도로거리의 절대오차를 이용하여 교차로 지역의 범위를 설정하고, 설정된 지역에서 차량의 진행각을 감지하여 교차로에 연결된 각 도로에 대한 출발지점을 알아내고, 회전각과 진행각을 비교하여 새로운 위치를 알아내는 방법이다. 제안된 알고리즘의 효율성을 검증하기 위하여 거리센서로 속도센서를, 방향센서로서 광 자이로를 이용하여 휴대용 컴퓨터에 시스템을 구성하고, 대전지역을 시범지역으로 선정하여 알고리즘을 실험한 결과 그 유효성을 입증할 수 있었다.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2010년 춘계학술발표회 논문집
• /
• pp.3-4
• /
• 2010

Map integration usually involves matching the common spatial objects in different datasets. There have been recent studies on object matching using relative location as defined by spatial relationships between the object and its neighbor landmark. Therefore the landmark selection process is an important part of map integration using relative location. In this research, we describe an approach to determine landmarks automatically in different geospatial datasets.

• 한국정밀공학회지
• /
• 제19권5호
• /
• pp.36-42
• /
• 2002

This paper presents the way of building an occupancy grid map which a mobile robot needs to autonomously navigate in the unknown environment. A disparity map resulting from stereo matching can be converted into the 2D distance information. If the stereo matching has some errors, however, the subsequent map becomes unreliable. In this paper, a new morphological filter is proposed to reject 'spikes' of the disparity map due to stereo mismatch by considering the fact that these spikes occur locally. The new method has advantages that it is simpler and more easily realized than existing similar algorithms. Several occupancy grid maps based on stereo vision using the proposed algorithm have been built and compared with the actual distance information to verify the validity of the proposed method.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.418-422
• /
• 2009

Generally, algorithms for generating disparity maps can be clssified into two categories: region-based method and feature-based method. The main focus of this research is to generate a disparity map with an accuracy depth information for 3-dimensional reconstructing. Basically, the region-based method and the feature-based method are simultaneously included in the proposed algorithm, so that the existing problems including false matching and occlusion can be effectively solved. As a region-based method, regions of false matching are extracted by the proposed MMAD(Modified Mean of Absolute Differences) algorithm which is a modification of the existing MAD(Mean of Absolute Differences) algorithm. As a feature-based method, the proposed method eliminates false matching errors by calculating the vector with SIFT and compensates the occluded regions by using a pair of adjacent SIFT matching points, so that the errors are reduced and the disparity map becomes more accurate.

• 제어로봇시스템학회논문지
• /
• 제21권10호
• /
• pp.965-971
• /
• 2015

This paper suggests a feature point-based Iterative Closest Point (ICP) algorithm to compensate for the disparity error in building a two-dimensional map. The ICP algorithm is a typical algorithm for matching a common object in two different images. In the process of building a two-dimensional map using the laser scanner data, warping and distortions exist in the map because of the disparity between the two sensor values. The ICP algorithm has been utilized to reduce the disparity error in matching the scanned line data. For this matching process in the conventional ICP algorithm, pre-known reference data are required. Since the proposed algorithm extracts characteristic points from laser-scanned data, reference data are not required for the matching. The laser scanner starts from the right side of the mobile robot and ends at the left side, which causes disparity in the scanned line data. By finding the matching points between two consecutive frame images, the motion vector of the mobile robot can be obtained. Therefore, the disparity error can be minimized by compensating for the motion vector caused by the mobile robot motion. The validity of the proposed algorithm has been verified by comparing the proposed algorithm in terms of map-building accuracy to conventional ICP algorithm real experiments.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 추계학술발표회 논문집
• /
• pp.141-146
• /
• 2003

In case of producing image map by using the color aerial photograph, DEM makes on huge effects to the accuracy of ortho image. Thus, this paper has the purpose that evaluate the accuracy of DEM acquired by matching the color aerial photograph. At the study, result of color aerial photograph's control point surveying was X=${\pm}$0.14m, f=${\pm}$0.16m. Estimated result by DEM of plot-map and matching has RMSE=${\pm}$1.058m for the elevation(Z). For matching DEM has a minor(-)'s value, it can access that produce by high point than plot-map DEM.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.99-102
• /
• 2009

In this paper a hierarchical stereo matching algorithm based on feature extraction is proposed. The boundary (edge) as feature point in an image is first obtained by segmenting an image into red, green, blue and white regions. With the obtained boundary information, disparities are extracted by matching window on the image boundary, and the initial disparity map is generated when assigned the same disparity to neighbor pixels. The final disparity map is created with the initial disparity. The regions with the same initial disparity are classified into the regions with the same color and we search the disparity again in each region with the same color by changing block size and search range. The experiment results are evaluated on the Middlebury data set and it show that the proposed algorithm performed better than a phase based algorithm in the sense that only about 14% of the disparities for the entire image are inaccurate in the final disparity map. Furthermore, it was verified that the boundary of each region with the same disparity was clearly distinguished.