• 대한원격탐사학회지
• /
• 제33권6_1호
• /
• pp.1019-1027
• /
• 2017

고해상도 위성영상의 활용이 가능해짐에 따라 다양한 분야에서 위성영상을 활용하고자 하는 연구가 진행되고 있다. 본 논문은 광역의 위성영상에서 특정 형태를 갖는 오브젝트를 탐지해내는 내용기반의 자동화된 표적 탐색 시스템의 전처리 단계를 위해 수학적 모폴로지 방법을 이용하여 말발굽 형상의 오브젝트를 추출하는 방법을 제안한다. 이는 촬영 지역 및 촬영 시기, 환경에 따라 영상 질의 차이가 심하고, 찾고자하는 표적의 에지가 선명하지 않은 위성영상에서도 쉽게 말발굽 형상의 오브젝트를 추출해내는 방법이다. 제안한 방법으로 말발굽 형상의 오브젝트를 빠르게 분류해냄으로써 다음 단계의 표적 탐지를 위해 탐색해야 할 영역의 수를 줄일 수 있으므로 시스템의 속도를 크게 향상 시킬 수 있다.

• 대한공간정보학회지
• /
• 제7권1호
• /
• pp.75-86
• /
• 1999

3차원 도시 모델은 여러 가지 인공구조물, 자연 지물 요소로 구성되며, 이 중에서 대부분을 차지하고 있는 것은 건물이다. 따라서 건물을 얼마나 정확하고 신속하게 추출하여 기존의 데이터베이스를 갱신할 수 있느냐는 중요한 문제라 할 수 있다. 이러한 문제의 해결 방안으로 DTM으로부터 추출한 건물 정보로 DTM을 재구성한다면, 이를 하나의 3차원 도시 모델로 이용할 수 있다. 따라서 본 연구는 고해상도 DTM과 항공사진의 edge 정보에 수리형태학(mathematical morphology) 및 영상분할 기법 등을 적용하여 건물의 윤곽선 및 높이 정보를 추출하는 것을 목적으로 한다. 본 연구의 결과, 수리형태학의 opening 연산을 통해 건물의 추출이 가능하였으며, 항공사진에서 추출한 edge 정보를 이용하여 건물 추출의 정확도를 향상시킬 수 있었다.

• 조명전기설비학회논문지
• /
• 제29권11호
• /
• pp.89-95
• /
• 2015

As a solution of improving the energy efficiency in power system, Low Voltage DC (LVDC) distribution systems different from conventional ones have been constantly researched. As in conventional AC distribution system, LVDC distribution system can suffer from High Impedance Fault (HIF) which may cause a failure of protective relay due to relatively low change in magnitude of fault current. In order to solve the problem, a scheme for detecting HIFs is presented in this paper. Closing Opening Difference Operation (CODO) based on Mathematical Morphology (MM), one of the MM-based filters, is utilized to make fault signals discriminable. To verify performance of the scheme, a simple LVDC distribution system is modeled by using ElectroMagnetic Transient Program (EMTP) software. Computer simulations according to various conditions are performed and comparison studies with a scheme using Wavelet Transform (WT) in an aspect of simulation time are also conducted.

• 전자공학회논문지S
• /
• 제34S권7호
• /
• pp.78-88
• /
• 1997

A three dimensional-two spatical dimensions plus time-image segmentation is widely used in a very low bit rate image sequence coding because it can solve the region correspondence problem. Mathematical morphology is a very efficient tool for the segmentation because it deals well with geometric features such as size, shape, contrast and connectivity. But if the motion in the image sequence is large in time axis, the conventional 3D morphological segmentation algorithm have difficulty in solving region correspondence problem. To alleviate this problem, we propose the hierarchical image sequence segmentation algorithm that uses the region motion information. Since the motion of a region in previous level affects that in current level uses the previous motion information to increase region correspondence. Simulation result shows improved performance for sequence frames with large motion.

• Journal of Electrical Engineering and Technology
• /
• 제11권1호
• /
• pp.234-240
• /
• 2016

We propose a novel framework for markerless camera-based games. By using a visual camera, our method may yield robust human body segmentation with high performance comparable to the segmentation using depth cameras. The edges of human bodies are detected by subtracting gradient backgrounds, and human body regions are segmented by the operations based on mathematical morphology. Collisions between detected regions and virtual objects are determined by finding the colliding time using intra-frame positions of virtual objects. Experimental results show that the proposed method may produce robust segmentation of human bodies, thereby and the collision responses are more accurate than previous methods. Therefore, the proposed framework can be widely used in camera-based games requiring high performance.

• 전자공학회논문지B
• /
• 제33B권8호
• /
• pp.68-80
• /
• 1996

In this paper, we propose a novel color image segmentation algorithm based on clustering in 3-dimensional color space employing the mathematical morphology. More specifically, since we take into account the topological properties such as the shape, connectivity and distribution of clusters in the clustering process, the number of clusters in the color cube, as well as their centers, can be easily obtained, without a priori knowledge on the input images. Intensive computer simulation has been performed and the results are discussed in this paper. The resutls of the simulation on the images in various color coordinates show that the segmentation is independent of the choice of color coordinates and the shape of clustes. Segmentation results of the vector quantizer are also presented for the comparison purpose.

• 전자공학회논문지B
• /
• 제33B권10호
• /
• pp.38-49
• /
• 1996

In this paper, we propose a fast hierarchical image segmentation using mathematical morphology. The proposed segmentation method is composed of five basic steps; multi-thresholding, open-close by reconstructing, mode operation, marker extraction, and region decision. In the multi-thresholding, an input image is simplified by Lloyd clustering algorithm. The multi-thresholded image then is more simplified by open-close by reconstruction and mode operating. In the region decision, to which region each uncertainty pixel belongs finally is decided by a watershed algorithm. Experimental results show that the quality of the segmentation results by the proposed method is not inferior to that by the conventional method and the average times elapsed by the proposed method can be reduced by one tghird of those elapsed by the conventional method.

• Journal of Ubiquitous Convergence Technology
• /
• 제1권1호
• /
• pp.18-22
• /
• 2007

Multi-Instance Learning(MIL) performs well to deal with inherently ambiguity of images in multimedia retrieval. In this paper, an effective framework for Contented-Based Image Retrieval(CBIR) with MIL techniques is proposed, the effective mechanism is based on the image segmentation employing improved Mean Shift algorithm, and processes the segmentation results utilizing mathematical morphology, where the goal is to detect the semantic concepts contained in the query. Every sub-image detected is represented as a multiple features vector which is regarded as an instance. Each image is produced to a bag comprised of a flexible number of instances. And we apply a few number of MIL algorithms in this framework to perform the retrieval. Extensive experimental results illustrate the excellent performance in comparison with the existing methods of CBIR with MIL.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.989-991
• /
• 1995

In this paper, we present a new morphological texture spectrum approach to obtain a surface orientation using the variation of texture image caused by projective distortions. Under the assumption that the surface of texture image is smooth continuous, and specially plane or sphere, we apply the mathematical morphology and texture spectrum in order to compute the 3-D surface orientation. If the surface of texture image is plane, the surface orientation can be obtained through a simple procedure. If the surface of texture image is sphere, we find the centroids of texels, and may compute several major axes, their slopes, and vanishing points. Using the texture spectrum between the intersections of the vanishing points and the size of elements in each texels, we can find the surface orientation of texels on the sphere.

• 한국통신학회논문지
• /
• 제17권10호
• /
• pp.1109-1116
• /
• 1992

Mathematical morphology는 이론적 배경으로 신호 및 시스템의 기하학적 특성을 해석하는데 우수하고 잡음이 섞인 데이터를 고르기에 있어서 매우 성공적으로 적용되고 있다. 본 논문에서는 morphological필터의 하드웨어 구현은 같은 회로에서 gray scale dilation과 erosion을 수행하여 최소값과 최대값을 선택하도록 함으로써 회로의 복잡성을 줄이고 병렬처리가 가능하도록 하였다. Morphological filter의 구조는 structuring element블록, 이미지 데이타 블록, 제어 블록, ADD 블록, MIN/MAX블록으로 구성되고 실시간 처리가 가능하도록 하드웨어를 설계, one chip화 한다.