• Journal of Digital Convergence
• /
• v.10 no.8
• /
• pp.239-247
• /
• 2012

This paper is related to an Object VR-based virtual textile wearing system carrying out textile texture mapping based on viewpoint vector estimation and intensity difference map. The proposed system is characterized as capable of virtually wearing a new textile pattern selected by the user to the clothing shape section segmented from multi-view 2D images of clothes model for Object VR(Object Virtual Reality), and three-dimensionally viewing its virtual wearing appearance at multi-view points of the object. Regardless of color or intensity of model clothes, the proposed system is possible to virtually change the textile pattern with holding the properties of the selected clothing shape section, and also to quickly and easily simulate, compare, and select multiple textile pattern combinations for individual styles or entire outfits. The proposed system can provide higher practicality and easy-to-use interface, as it makes real-time processing possible in various digital environment, and creates comparatively natural and realistic virtual wearing styles, and also makes semi-automatic processing possible to reduce the manual works.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.5
• /
• pp.125-135
• /
• 2012

This paper proposes the new object detection system with two laser-scanners and a camera for classifying the objects and predicting the location of objects on road street. This detection system could be applied the new C-ITS service such as ADAS(Advanced Driver Assist System) or (semi-)automatic vehicle guidance services using object's types and precise position. This study describes the some examples in other countries and feasibility of object detection system based on a camera and two laser-scanners. This study has developed the heterogenous sensor's fusion method and shows the results of implementation at road environments. As a results, object detection system at roadside infrastructure is a useful method that aims at reliable classification and positioning of road objects, such as a vehicle, a pedestrian, and obstacles in a street. The algorithm of this paper is performed at ideal condition, so it need to implement at various condition such as light brightness and weather condition. This paper should help better object detection and development of new methods at improved C-ITS environment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.125-131
• /
• 2016

Tongue image segmentation is critical for automation of the tongue diagnosis system. However, most image segmentation methods for tongue diagnosis systems in oriental medicine have been proposed as user-based manual types or semi-automatic types. This study proposed a new method for tongue image segmentation, which is the most important image processing stage for complete automation of the tongue diagnosis system in oriental medicine. The proposed method improved the conventional snake algorithm, by making improvement on the internal energy function so that, as the points move outward reversely, the snake energy function is minimized, by using the image characteristics of tongue images. To calculate external energy, hierarchical spatial filtering is applied to ensure resistance against noise. Also, The proposed method was tested by using sample images and actual images, and showed more robustness against the background noise than the conventional snake algorithm. And, when one selected point was moved by the improved snake algorithm, energy values at the starting, middle, and end points were analyzed, and showed robustness that does not fall in the local minima.

• Journal of the Ergonomics Society of Korea
• /
• v.36 no.1
• /
• pp.37-52
• /
• 2017

Objective: The present study developed a user-centered 3D virtual liver surgery planning (VLSP) system called Dr. Liver to provide preoperative information for safe and rational surgery. Background: Preoperative 3D VLSP is needed for patients' safety in liver surgery. Existing systems either do not provide functions specialized for liver surgery planning or do not provide functions for cross-check of the accuracy of analysis results. Method: Use scenarios of Dr. Liver were developed through literature review, benchmarking, and interviews with surgeons. User interfaces of Dr. Liver with various user-friendly features (e.g., context-sensitive hotkey menu and 3D view navigation box) was designed. Novel image processing algorithms (e.g., hybrid semi-automatic algorithm for liver extraction and customized region growing algorithm for vessel extraction) were developed for accurate and efficient liver surgery planning. Usability problems of a preliminary version of Dr. Liver were identified by surgeons and system developers and then design changes were made to resolve the identified usability problems. Results: A usability testing showed that the revised version of Dr. Liver achieved a high level of satisfaction ($6.1{\pm}0.8$ out of 7) and an acceptable time efficiency ($26.7{\pm}0.9 min$) in liver surgery planning. Conclusion: Involvement of usability testing in system development process from the beginning is useful to identify potential usability problems to improve for shortening system development period and cost. Application: The development and evaluation process of Dr. Liver in this study can be referred in designing a user-centered system.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.309-313
• /
• 2017

개체명은 인명, 지명, 조직명 등 문서 내에서 중요한 의미를 가지므로 질의응답, 요약, 기계번역 분야에서 유용하게 사용되고 있다. 개체명 인식은 문서에서 개체명에 해당하는 단어를 찾아 개체명 범주를 부착하는 작업을 말한다. 개체명 인식 연구에는 개체명 범주가 부착된 개체명 말뭉치를 사용한다. 개체명의 범주는 연구 분야에 따라 다양하게 정의되므로 연구 분야에 적합한 개체명 말뭉치가 필요하다. 하지만 이런 말뭉치를 구축하는 일은 시간과 인력이 많이 필요하다. 따라서 본 논문에서는 개체명 사전 기반의 반자동 말뭉치 구축 도구를 제안한다. 제안하는 도구는 크게 전처리, 사용자 태깅, 후처리 단계로 나뉜다. 전처리 단계는 자동으로 개체명을 찾는 단계이다. 약 11만 개의 개체명을 기반으로 하여 트라이(trie) 구조의 개체명 사전을 구축한 후 사전을 이용하여 개체명을 자동으로 찾는다. 사용자 태깅 단계는 사용자가 수동으로 개체명을 태깅하는 단계이다. 전처리 단계에서 찾은 개체명 중 오류가 있는 개체명들은 수정하거나 삭제하고, 찾지 못한 개체명들은 사용자가 추가로 태깅하는 단계이다. 후처리 단계는 태깅한 결과로부터 사전 정보를 갱신하는 단계이다. 제안한 말뭉치 구축 도구를 이용하여 752개의 뉴스 기사에 대해 개체명을 태깅한 결과 7,620개의 개체명이 사전에 추가되었다. 제안한 도구를 사용한 결과 사용하지 않았을 때 비해 약 57.6% 정도 태깅 횟수가 감소했다.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.120-120
• /
• 2017

최근 국내 소비자들의 안전한 음식과 환경문제에 대한 관심이 높아지면서 재배작물과 경작지 토양의 물리 화학적 특성 등에 맞추어 적정 시비 및 재배관리를 적용하는 정밀농업이 시도되고 있다. 정밀농업은 농약 및 비료 등의 양을 적절하게 사용하여 생산 비용을 절감할 수 있으며, 과다사용을 막아 환경오염을 줄일 수 있다. 현재 토양의 수분, EC, pH등과 같은 항목은 신속하고 간단하게 분석이 가능하지만 토양의 필수 원소인 N, P, K 성분을 분석하는 제품은 상용화 되지 않았거나 가격이 비싸 일반 농가에서는 사용이 어렵다. 특히, 토양의 인을 현장에서 분석하기 위한 연구가 많이 수행되고 있으나 실제로 현장에서 사용되는 경우 또한 없는 상황이다. 일반적으로 토양에 포함되어 있는 인을 측정하기 위해서 많은 실험실에서는 이화학적 분석법을 사용하고 있다. 하지만 이 분석법은 오랜 시간과 전문적인 인력이 필요하며 주변 환경변화에 민감하여 실시간으로 분석하기에는 어렵다고 한다. 따라서 본 연구에서는 현장에서 실시간으로 토양의 인을 분석하기 위해 반자동 분석시스템을 제작하고 이를 검증하고자 하였다. 이전 연구에서 현장 토양을 이용한 신속측정법의 가능성($R^2>0.7$)을 확인하여 이 분석법을 바탕으로 반자동 분석시스템을 제작하였고 표준결과 값의 약 70% 이상의 수준을 목표로 하였다. 진주 지역의 현장 토양 20개 샘플과 반자동 침출 장치, 여과 장치, 발색 장치 그리고 통합 반자동 시스템을 이용하여 분석한 후 표준 분석 결과와 비교하였을 때 $R^2$ 값이 각각 0.985, 0.817, 0.893, 0.837로 약 70% 이상의 수준을 달성하였다. 추후, 반자동 토양 인 신속측정시스템을 완전 자동화 시스템으로 개발하고 주행 장치를 부착시켜 현장에서 실시간으로 원하는 위치의 인을 측정 할 수 있을 것으로 판단된다.

• Journal of Broadcast Engineering
• /
• v.11 no.3 s.32
• /
• pp.284-301
• /
• 2006

In this paper, we present a design and implementation of a TV-Anytime metadata authoring tool for providing personalized data-broadcasting services. The TV-Anytime specifies metadata schema, metadata coding and delivery, and provides service models to provide personalized broadcasting content services at anytime when users want to consume using metadata including ECG (Electronic Content Guide) and content descriptive information in a PDR (Personal Digital Recorder)-centric environment. In spite of a useful services based on TV-anytime metadata, the metadata authoring still remains as a harassing and time consuming task. For easy metadata authoring, the proposed metadata authoring provides the following key functionalities: metadata visualization, media access, and semi-automatic method for editing segment related metadata.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.437-448
• /
• 2004

This paper presents an approach to the development of bio-ontology using the Object-oriented Ontology Manager(OOM). OOM views a term of an ontology as an object which can be an instance or a concept. OOM facilitates the semi-automatic construction of ontologies by an intuitive interface and by inferencing with links among complicated and informative ontology terns. The main advantage of OOM is simple-to-use not compromising expressiveness so that ontologies in a complicated domain such as bioinformatics can be modeled intuitively. The ontologies constructed by OOM are easily exported to ontologies in other ontology languages without semantic loss because the structures of both the ontology by OOM and the ontologies in most of standard ontology languages are analogous. A translator to another standard ontology language is also provided by OOM so that the ontology can be combined with others to be applied to more complicated applications.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.11
• /
• pp.1405-1411
• /
• 2012

Remote handling manipulators are widely used for performing hazardous tasks, and it is essential to ensure the reliable performance of such systems. Toward this end, tendon-driven mechanisms are adopted in such systems to reduce the weight of the distal parts of the manipulator while maintaining the handling performance. In this study, several approaches for the design of a gripper system for a tendon-driven remote handling system are introduced. Basically, this gripper has an underactuated spring mechanism that is combined with a slave manipulator triggered by a master operator. Based on the requirements under the specified tendon-driven mechanism, the connecting position of the spring system on the gripper mechanism and kinematic influence coefficient (KIC) analysis are performed. As a result, a suitable combination of components for the proper design of the target system is presented and verified.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.3
• /
• pp.243-251
• /
• 2016

LiDAR data processing steps include noise removal, filtering, classification, segmentation, shape recognition, modeling, and quality assessment. This paper focuses on modeling and accuracy evaluation of 3D objects with curved surfaces. The appropriate modeling functions were determined by analyzing surface patch shape. Existing methods for modeling curved surface features require linearization, initial approximation, and iteration of the non-linear functions. However, proposed method could directly estimate the unknown parameters of the modeling functions. The results demonstrate feasibility of the proposed method. The proposed method was applied to the simulated and real building data of hemi-spherical and semi-cylindrical surfaces. The parameters and accuracy of the modeling functions were estimated. It is expected that the proposed method would contribute to automatic modeling of various objects.