• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.79-82
• /
• 2012

컴퓨터 비전에서 영상 매칭 기술은 다양한 분야에 응용될 수 있는 기초적인 기술 중에 하나이다. 강인한 영상 매칭을 위해서는 정확하고 독특한 특징점을 검출하는 과정이 중요하다. 기존의 SIFT나 SURF 등 영상 매칭 알고리즘은 등방성 가우시안 필터링을 사용한 스케일 공간을 생성하여 특징점을 검출한다. 이러한 기존의 특징점 검출 방식은 스케일 공간에서 영상의 경계선을 모호하게 만들어 정확한 특징점 검출을 어렵게 만들고 영상 매칭의 성능을 떨어뜨리는 문제점을 가지고 있다. 본 논문에서는 SIFT 알고리즘의 강인한 특징점 검출을 위하여 양방향 필터링을 사용하여 스케일 공간 생성을 제안한다. 이러한 스케일 공간 생성 방식은 스케일 공간에서 영상의 경계선을 보존해 줌으로서 강인한 특징점 검출을 가능하게 하여 영상 매칭 성능을 향상시킨다. 특히 왜곡이 존재하는 영상들의 매칭에서 제안하는 특징점 검출 방법이 적용된 SIFT 알고리즘은 기존의 SIFT 알고리즘보다 우수한 영상 매칭 결과를 보여준다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.1
• /
• pp.23-28
• /
• 2013

The process of a feature matching for two different spatial data sets is similar to the process of classification as a binary class such as matching or non-matching. In this paper, we calculated a threshold by applying an equal error rate (EER) which is widely used in biometrics that classification is a main topic into spatial data sets. In a process of discriminating what's a matching or what's not, a precision and a recall is changed and a trade-off appears between these indexes because the number of matching pairs is changed when a threshold is changed progressively. This trade-off point is EER, that is, threshold. To the result of applying this method into training data, a threshold is estimated at 0.802 of a value of shape similarity. By applying the estimated threshold into test data, F-measure that is a evaluation index of matching method is highly value, 0.940. Therefore we confirmed that an accurate threshold is calculated by EER without person intervention and this is appropriate to matching different spatial data sets.

• Journal of Korean Society for Geospatial Information Science
• /
• v.17 no.4
• /
• pp.23-29
• /
• 2009

Recent growth of the geospatial information on the Web has made it possible to easily access a wide variety of geospatial information. An integration of different geospatial objects consists of the following three steps; extracting geospatial objects from the maps, converting the coordinate system and discovering pairs of objects that represent the same real-world entity in the two maps. This paper deals mainly with the third step to correspond conjugate objects and four matching types and criteria is presented. The techniques designed and developed can be utilized to efficiently integrate distributed heterogeneous spatial databases such as the digital maps and POIs from other data sources. To achieve the goal, we presented four types and criteria for the matching schema. The main contributions of this paper are as follows. A complete process of integrating data from maps on the Web is presented. Then, we show how attributes of the objects can be used in the integration process.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.15-17
• /
• 2010

인터넷이나 모바일 기기를 이용한 지도 서비스를 이용하는 사용자가 많아지고 그에 따라 다양한 형태의 서비스가 제공되고 있어 이를 위한 자료 구축의 필요성이 커지고 있다. 이종의 자료를 Conflation하여 직관적으로 사용자가 공간정보를 얻을 수 있게 하기 위해서는 자료 간에 공간 편이가 없어야 하나 다양한 원인으로 인해 공간 불일치가 발생하고 있어 이를 조정하는 것이 필요하다. 이를 위해서 도로의 교차로에서 템플릿을 형성하고 도로 후보영상과 매칭을 수행하여 자료간 조정을 수행하였다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.3
• /
• pp.101-108
• /
• 2012

The construction of data connection is required due to the digital map do not have the new address data which is implemented by the Korea government and it cannot use between government and other agency. The manually matching of digital map and new address data is time and money consuming process due to the huge amount of data. In this research, new system is developed for data generation of attribute data by the data connection method of digital map and new address data using spatial matching and matching rate of data connection is analyses. The results of data matching rate in the research area are 84% in building case and 67% in road case in 1:1000 digital map at Suwon and 18% in building case and 21% in road at Seogwipo.

• 한국지형공간정보학회:학술대회논문집
• /
• 2004.10a
• /
• pp.25-31
• /
• 2004

To obtain the 3-D coordinates of the urban roads from aerial images, the accurate matching technique in road areas is required. In this paper, we suggest the relational matching method that is performed by comparison of relationships of road pavement markings after they are extracted from aerial images using geometric properties and spatial relationships of the pavement markings. Relational matching requires not only high level description of features but also the solution for inexact matching problems. In addition, it needs a lot of tests for the reliable final result. In this research, we described features as calculating geometric properties of the pavement markings, suggested the solution for inextact matching problems, and performed tests to decide whether the result is acceptable or not, which use the property that road areas are flat. In order to evaluate the accuracy of matching, we made a visual evaluation and compared the result of this technique with those measured by analytical photogrammetry.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.188-191
• /
• 2010

스테레오 매칭은 Robot Vision 분야에서 가장 활발하게 연구가 진행되어온 주제이다. 과거 많은 연구들은 스테레오 매칭 알고리즘의 정확도를 높이거나 처리속도를 개선하는 것 중 어느 한 쪽에만 집중하고 있었으며, 두 가지를 동시에 고려한 연구는 상대적으로 연구가 미흡한 실정이다. 본 논문에서는 영상의 공간적 중복 성질을 이용하여 스테레오 매칭 알고리즘의 처리속도를 획기적으로 개선하는 방법을 제안하고, 처리 속도 감소에 따라 증가되는 disparity map 추정 오차를 보상하는 기술을 제안한다. 구체적으로 Dynamic Programming (DP) 기반 스테레오 매칭 알고리즘에 제안한 속도 개선 방법을 적용하고, 개선된 Adaptive Support Weight Filter를 사용하여 보다 효과적인 오차 보상을 실현 하였다. 체계적인 실험을 통해, 본 논문에서 제안 하는 스테레오 매칭 알고리즘은 처리속도와 정확도를 동시에 개선할 수 있음을 검증하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10a
• /
• pp.575-577
• /
• 2000

DNA 염기 서열을 분석하는데 효율적으로 쓸 수 있는 자료구조서 서픽스 트리(Suffix Tree)가 제시되었다. 그러나 매우 큰 유전자 서열에 대한 서픽스 트리는 대용량의 메모리 공간을 필요로 한다. 따라서 메모리 공간의 절약을 위해서 단어 서픽스 트리를 이용하는 방법이 제안되었다. 단어 서픽스 트리는 이러한 장점에도 불구하고 단어에 의미를 두고 만든 트리 구조이기 때문에 완전 매칭 문제를 해결하기 위한 정보가 부족해서 제한적 완전 매칭 알고리즘이 제시되었다. 제한적 완전 매칭 알고리즘에서는 찾으려는 패턴이 어떤 단어의 부-문자열에 위치하거나, 두 단어 이상에 걸쳐 나오면 찾지 못하는 문제가 발생한다. 본 논문에서는 단어 서픽스 트리의 완전 매칭 문제를 해결하기 위해 각 단어들의 서픽스에 대한 정보로 구성된 Generalized 서픽스 트리를 사용하여 확장된 단어 서픽스 트리를 제시하고, 완전 매칭 알고리즘을 제안한다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.1
• /
• pp.89-98
• /
• 2016

In this paper, we proposed an automated areal feature matching method based on geometric similarity without user intervention and is applied into areal features of many-to-many relation, for confusion of spatial data-sets of different scale and updating cycle. Firstly, areal feature(node) that a value of inclusion function is more than 0.4 was connected as an edge in adjacency matrix and candidate corresponding areal features included many-to-many relation was identified by multiplication of adjacency matrix. For geometrical matching, these multiple candidates corresponding areal features were transformed into an aggregated polygon as a convex hull generated by a curve-fitting algorithm. Secondly, we defined matching criteria to measure geometrical quality, and these criteria were changed into normalized values, similarity, by similarity function. Next, shape similarity is defined as a weighted linear combination of these similarities and weights which are calculated by Criteria Importance Through Intercriteria Correlation(CRITIC) method. Finally, in training data, we identified Equal Error Rate(EER) which is trade-off value in a plot of precision versus recall for all threshold values(PR curve) as a threshold and decided if these candidate pairs are corresponding pairs or not. To the result of applying the proposed method in a digital topographic map and a base map of address system(KAIS), we confirmed that some many-to-many areal features were mis-detected in visual evaluation and precision, recall and F-Measure was highly 0.951, 0.906, 0.928, respectively in statistical evaluation. These means that accuracy of the automated matching between different spatial data-sets by the proposed method is highly. However, we should do a research on an inclusion function and a detail matching criterion to exactly quantify many-to-many areal features in future.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.1 s.15
• /
• pp.73-84
• /
• 2000

Map matching technique is an essential part of the car navigation and other related positioning fields such as dead reckoning and GPS data logging upon the GIS database. This paper is to break down map matching techniques, to categorize them, and to propose a simple technique for GPS based map matching technique. For categorization of techniques, two approaches have been adopted. One is to only use geometric information, and the other is to use both geometric and topological information. Some pros and cons of each method have been described. In addition, a simple map matching technique, set forth in this paper, has been introduced for properly utilizing the advantage of GPS points after the absence of the chronic problem of selective availability, which had been prevailed recently. Some research opportunities and problems of the technique have also been discussed.