http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
예철수,이쾌희,Ye, Chul-Soo,Lee, Kwae-Hi 대한전자공학회 2000 電子工學會論文誌-SP (Signal processing) Vol.37 No.4
본 논문에서는 스테레오 항공 영상으로부터 영상에 포함된 건물의 3차원 복원을 위해 건물 형태에 대한 모델을 생성하고 건물 모델을 구성하는 선소를 찾아 건물을 복원하는 알고리듬에 대해 다루고 있다. 건물을 검출하기 위해 일반적으로 필요한 에지 검출, 에지의 직선화, 선소의 연결 등의 복잡한 과정을 거치지 않고 복원하는 건물을 몇 개의 파라미터값으로 표현하고 건물 모델을 이용하여 원영상에서 건물의 선소들을 직접 검출하는 새로운 방법을 제안하였다. 선소 검출시 건물을 구성하는 각각의 선소에 대해 선소 측정 함수를 동시에 적용하여 독립적인 선소 검출 방법보다 건물 검출의 정확도를 높였다. 제안한 알고리듬을 스테레오 항공 영상에 적용한 결과, 건물의 정확한 검출 및 복원 결과를 얻을 수 있었다. This paper presents an algorithm for 3D building reconstruction from a pair of stereo aerial images using the 3D building model and the linear segments of building. Direct extraction of linear segments from original building images using parametric building model is attempted instead of employing the conventional procedures such as edge detection, linear approximation and line linking A segment measure function is simultaneously applied to each line segment extracted in order to improve the accuracy of building detection comparing to individual linear segment detection. The algorithm has been applied to pairs of stereo aerial images and the result showed accurate detection and reconstruction of buildings.
이우영 ( Woo Young Lee ),엄기문 ( Gi Mun Um ),박찬응 ( Chan Eung Park ),이쾌희 ( Kwae Hi Lee ) 大韓遠隔探査學會 1993 大韓遠隔探査學會誌 Vol.9 No.2
In stereo vision, when we use two parallel axis images, small portion of object is contained and B/H(Base-line to Height) ratio is limited due to the size of object and depth information is inaccurate. To overcome these difficulties we take a non-parallel axis image which is rotated θ about y-axis and match other parallel-axis image. Epipolar lines of non-parallel axis image are not same as those of parallel-axis image and we can`t match these two images directly. In this paper, we transform the non-parallel axis image geometrically with camera parameters, whose epipolar lines are alingned parallel. NCC(Normalized Cross Correlation) is used as match measure, area-based matching technique is used to find correspondence and 9×9 window size is used, which is chosen experimentally. Focal length which is necessary to get depth information of given object is calculated with least-squares method by CCD camera characteristics and lenz property. Finally, we select 30 test points from given object whose elevation is varied to 150 mm, calculate heights and know that height RMS error is 7.9 mm.
예철수 ( Chul Soo Ye ),이쾌희 ( Kwae Hi Lee ) 大韓遠隔探査學會 2002 大韓遠隔探査學會誌 Vol.18 No.2
Watershed 알고리듬을 통해 에지 기반과 영역 기반 기법을 결합한 하이브리드 영상 분할 알고리듬을 제안하였다. 먼저 min/max flow와 결합된 평균 곡률 확산을 이용하여 에지를 보존하면서 잡음을 제거를 수행한다. 영상을 watershed 알고리듬을 이용하여 분할한 후에 RAG Region Adjacency Graph)을 사용하여 분할된 영역들간의 관계를 분석한다. RAG의 그래프 노드와 에지 비용은 분할된 영역과 두 인접한 영역사이의 상이함을 나타낸다. 최소 비용의 RAG의 에지를 찾아 가장 유사한 영역 쌍이 결정되면 두 영역은 서로 합치고 RAG은 갱신된다. 제안한 방법을 통해서 잡음을 효과적으로 감소시키고 한 화소 두께의, 닫힌 경계선을 획득할 수 있었다. A hybrid image segmentation algorithm is proposed which integrates edge-based and region-based techniques through the watershed algorithm. First, by using mean curvature diffusion coupled to min/max flow, noise is eliminated and thin edges are preserved. After images are segmented by watershed algorithm, the segmented regions are combined with neighbor regions. Region adjacency graph (RAG) is employed to analyze the relationship among the segmented regions. The graph nodes and edge costs in RAG correspond to segmented regions and dissimilarities between two adjacent regions respectively. After the most similar pair of regions is determined by searching minimum cost RAG edge, regions are merged and the RAG is updated. The proposed method efficiently reduces noise and provides one-pixel wide, closed contours.
위성 영상 분류를 위한 규칙 기반 훈련 집합 선택에 관한 연구
엄기문(Um Gi Mun),이쾌희(Lee Kwae Hi) 한국정보처리학회 1996 정보처리학회논문지 Vol.3 No.7
The conventional training set selection methods for the satellite image classification usually depend on the manual selection using data from the direct measurements of the ground or the ground map. However this task takes much time and cost, and some feature values vary in wide ranges even if they are in the same class. Such feature values can increase the robustness of the neural net but learning time becomes linger. In this paper, we propose a new training set selection algorithm using a rule-based method. By the technique proposed, the SPOT multispectral Imagery is classified in 3 bands, and the pixels which satisfy the rule are employed as the training sets for the neural net classifier. The experimental results show faster initial covergence and almost the same or better classification accuracy. We also showed an improvement of the classification accuracy by using texture features and NDVI.