• Journal of KIISE
• /
• v.43 no.9
• /
• pp.1034-1042
• /
• 2016

Together with machine-learning frameworks, area-based imagery registration techniques can be easily applied to diverse types of image pairs without predefined features and feature descriptors. However, feature detectors are often used to quickly identify candidate image patch pairs, limiting the applicability of these registration techniques. In this paper, we propose a ConvNet (Convolutional Network) "Dart" that provides not only the matching metric between patches, but also information about their distance, which are helpful in reducing the search space of the corresponding patch pairs. In addition, we propose a ConvNet "Fad" to identify the patches that are difficult for Dart to improve the accuracy of registration. These two networks were successfully implemented using Deep Learning with the help of a number of training instances generated from a few registered image pairs, and were successfully applied to solve a simple image registration problem, suggesting that this line of research is promising.

• Proceedings of the KSRS Conference
• /
• 2006.03a
• /
• pp.49-52
• /
• 2006

최근 대규모 지역 혹은 전 지구에 걸친 분석 및 모니터링을 위한 위성영상의 사용이 늘어나면서 이를 처리하기 위한 효율적인 '영상좌표 상호등록'법이 요구되고 있다. 이에 본 연구에서는 일반적으로 오랜 시간이 소요되는 '영상좌표 상호등록'의 효율성을 높이기 위해 '사전검수영역기반정합법'(Pre-qualified area based matching)을 사용하였다. 이를 통해 '영상좌표 상호등록'시 연산시간을 현저히 단축시켰고 추출된 정합점에 과대오차제거법을 적용함으로서 단순히 영역기반정합법을 적용한 경우에 비해서 정확도가 향상됨을 확인할 수 있었다. 제안한 알고리즘을 이용하여 테스트 프로그램을 작성, 한반도 Landsat ETM+ 영상 3장을 이용하여 테스트하였다. 정합점 간의 평균제곱오차는 0.436 영상소, 정합점은 평균 38,475개로 나타났다. 연산시 간은 평균 약 8분으로 나타났다.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.83-92
• /
• 2006

This paper describes an image disparity estimation method using region-based stereo matching. Region-based disparity estimation yields a disparity map as the unit of segmented region. However it estimates disparity imprecisely because it not only has matching errors but also applies an identical way to disparity estimation, which does not consider each type of matched regions. To solve this problem, we proposes a disparity estimation method which considers the type of matched regions. That is, the proposed method classifies whole matched regions into a similar-matched region, a dissimilar-matched region, a false-matched region and a miss-matched region. We then performs proper disparity estimation for each type of matched regions. This method minimizes the error in estimating disparity which is caused by inaccurate matching and also improves the accuracy of disparity of the well-matched regions. The experimental results show the improved accuracy of the proposed method.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.2
• /
• pp.143-152
• /
• 2012

It is well-known that image matching is necessary for automatic generation of 3D data such as digital surface data from aerial images. Recently developed aerial digital cameras allow to capture multi-strip images with higher overlaps and less occluded areas than conventional analogue cameras and that much of researches on multi-image matching have been performed, particularly effective methods of measuring a similarity among multi-images using point features as well as linear features. This research aims to investigate similarity measuring methods such as SSD and SNCC incorporated into a area based multi-image matching method based on vertical line locus. In doing this, different similarity measuring entities such as grey value, grey value gradient, and average of grey value and its gradient are implemented and analyzed. Further, both dynamic and pre-fixed adaptive-window size are tested and analyzed in their behaviors in measuring similarity among multi-images. The aerial images used in the experiments were taken by a DMC aerial frame camera in three strips. The over-lap and side-lap are about 80% and 60%, respectively. In the experiment, it was found that the SNCC as similarity measuring method, the average of grey value and its gradient as similarity measuring entity, and dynamic adaptive-window size can be best fit to measuring area-based similarity in area based multi-image matching method based on vertical line locus.

• Journal of Korean Society for Geospatial Information Science
• /
• v.12 no.2 s.29
• /
• pp.61-66
• /
• 2004

By the advent of the high-resolution Satellite imagery, there are increasing needs in image mosaicking technology which can be applied to various application fields such as GIS(Geographic Information system). To mosaic images, various methods such as image matching and histogram modification are needed. In this study, automated image mosaicking is performed using image matching method based on the multi-resolution wavelet analysis(MWA). Specifically, both area based and feature based matching method are embedded in the multi-resolution wavelet analysis to construct seam line.; seam points are extracted then polygon clipping method are applied to define overlapped area of two adjoining images. Before mosaicking, radiometric correction is proceeded by using histogram matching method. As a result, mosaicking area is automatically extracted by using polygon clipping method. Also, seamless image is acquired using multi-resolution wavelet analysis.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.661-664
• /
• 2001

본 논문에서는 영상을 특성에 따라 국부 영역으로 분류하고 변위 공간(disparity space)상에서의 특징을 분석하여 각각의 영역에 적합한 윈도우의 크기를 정하는 새로운 스테레오 정합 기법을 제안한다. 일반적으로 텍스쳐(texture)가 적은 영역이나 텍스쳐가 반복되는 영역, 그리고 깊이의 불연속선상에서는 고정된 크기의 윈도우를 사용하는 영역 기반 스테레오 기법은 잘 동작하지 않는다. 본 논문에서는 이러한 영역들의 변위 공간상에서의 정합 값 분포를 분석하여 스테레오 정합에 이용한다. 실험은 변위의 참값이 알려진 영상에 대해서 수행되었으며 기존의 방법에 비해 짧은 수행 시간 및 정확한 정합 결과를 보여 준다.

• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.612-624
• /
• 2005

In this paper, we propose a surface-based registration using a gaussian weighted distance map for PET-CT brain image fusion. Our method is composed of three main steps: the extraction of feature points, the generation of gaussian weighted distance map, and the measure of similarities based on weight. First, we segment head using the inverse region growing and remove noise segmented with head using region growing-based labeling in PET and CT images, respectively. And then, we extract the feature points of the head using sharpening filter. Second, a gaussian weighted distance map is generated from the feature points in CT images. Thus it leads feature points to robustly converge on the optimal location in a large geometrical displacement. Third, weight-based cross-correlation searches for the optimal location using a gaussian weighted distance map of CT images corresponding to the feature points extracted from PET images. In our experiment, we generate software phantom dataset for evaluating accuracy and robustness of our method, and use clinical dataset for computation time and visual inspection. The accuracy test is performed by evaluating root-mean-square-error using arbitrary transformed software phantom dataset. The robustness test is evaluated whether weight-based cross-correlation achieves maximum at optimal location in software phantom dataset with a large geometrical displacement and noise. Experimental results showed that our method gives more accuracy and robust convergence than the conventional surface-based registration.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.3
• /
• pp.76-88
• /
• 1999

본 논문에서는 건물이 포함된 스테레오 영상으로부터 건물을 3차원적으로 복원하기 위한 선소 특징 기반 정합 알고리듬에 대해 다루고 있다. 기존의 선소 특징 기반 정합 알고리듬은 선소 추출 기법의 성능에 많이 의존하고, 좌우 영상에서 추출된 에지 길이와 방향이 서로 차이가 날 경우 오정합이 많이 발생한다. 따라서, 건물의 형태를 올바르게 나타내지 못하는 원인이 된다. 본 논문에서는 이러한 단점을 해결하기 위하여 선소의 중심 및 양 끝점 외에 선소에 방향까지 고려하는 새로운 탐색 영역 설정 방법을 제안하였다. 또한 선소기반 정합에서 정합이 잘 이뤄지지 않는 수평선 정합 문제를 해결하기 위한 새로운 방법을 제안하였다. 한편 편평한 건물 가정 하에서 미정합된 건물 내부의 변이값을 얻기 위해 건물 추출 결과와 정합된 선소들을 이용한 보간법을 사용하였다. 제안한 알고리듬을 스테레오 항공 영상에 적용한 결과, 기존의 Hussien 등이 제안한 알고리듬에 비해 좋은 성능을 보였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.443-445
• /
• 1998

스트레오 영상 처리에 있어서 가장 중요한 단계는 좌우 영상간의 일치점을 찾는 영상 정합 단계라고 할 수 있다. 일반적인 영상 정합 방법으로는 영역 기반에 의한 방법과 특징점에 기반한 방법으로 나누어질 수 있다. 영역 기반의 방법은 많은 계산량을 필요로 하는 단점이 있으며, 특징점에 기반한 방법은 처리 속도는 향상시킬 수 있으나 전체적인 변이도를 구할 수 없는 단점이 있다. 한편 이미지 데이터 자체의 애매함이나 잡음, 처리 과정에서 발생하는 모호성, 인식과 해석 단계에서의 불확실한 지식등을 효과적으로 다루기 위해 퍼지 기법을 이용한 영상 처리 연구가 활발히 진행되고 있다. 본 논문에서는 각 픽셀의 밝기를 소속함수 값으로 변환한 후, 이 소속함수 값을 이용하여 좌우 영상의 일치점을 찾는 퍼지 스테레오 정합 알고리듬을 제안한다. 제안된 알고리듬은 몇 가지 스테레오 영상에 적용하여 그 유효성을 입증한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.85-90
• /
• 1998

The most important step image processing is stereo matching process. That is finding pixels of 3 dimensional pair in the left and right image. There are two matching methods. One is an area based approach and the other is a feature based approach. An area based approach needs much calculation time. In the other hand, we have the advantage of calculation time in the feature based approach, but can not obtain matched data for all pixels in the image. In recent years, fuzzy image processing methods are developed to manage vagueness and noise in image and ambiguous, inconsistent knowledge in recognition step. In this paper, we propose a fuzzy stereo matching algorithm. This method converts brightness data of image to fuzzy membership value and processes an area based approach method for stereo matching algorithm. We experiment with some stereo images to validate effectiveness of this algorithm.