• 로봇학회논문지
• /
• 제3권3호
• /
• pp.245-254
• /
• 2008

Recently, many vision-based navigation methods have been introduced as an intelligent robot application. However, many of these methods mainly focus on finding an image in the database corresponding to a query image. Thus, if the environment changes, for example, objects moving in the environment, a robot is unlikely to find consistent corresponding points with one of the database images. To solve these problems, we propose a novel navigation strategy which uses fast motion estimation and a practical scene recognition scheme preparing the kidnapping problem, which is defined as the problem of re-localizing a mobile robot after it is undergone an unknown motion or visual occlusion. This algorithm is based on motion estimation by a camera to plan the next movement of a robot and an efficient outlier rejection algorithm for scene recognition. Experimental results demonstrate the capability of the vision-based autonomous navigation against dynamic environments.

• 디지털콘텐츠
• /
• 1호통권128호
• /
• pp.152-156
• /
• 2004

• 디지털콘텐츠학회 논문지
• /
• 제18권8호
• /
• pp.1627-1633
• /
• 2017

인체의 댄스 학습은 실제로 수업을 참여하지 않고는 복잡하고 연속적인 신체 움직임으로 이루어진 전문가의 동작을 효과적으로 따라 하기는 어렵다. 본 논문에서는 인체 깊이 정보를 이용한 댄스 학습 시스템을 제안하고 있다. 제안한 시스템에서는 마커 프리 동작 갭쳐를 활용하여 댄스 전문가들로부터 다양한 예제 동작들을 갭쳐하고, 온라인 댄스 레슨에 사용하기 위해 동작 데이터베이스에 저장한다. 학생은 타블렛이나 키오스크 PC와 같은 사용자 단말기를 통해 데이터베이스에서 원하는 동작을 선택하고, 학습한 후 자신의 동작을 온라인 피드백을 받기 위해 강사에게 전송할 수 있다. 이 학습 과정에서 본 시스템은 네트워크 환경에서 학생과 강사가 효율적으로 동작 데이터를 교환하기 위해 빠르게 동작을 검색할 수 있는 방법과 다중 모드 화면을 제공한다. 실험 결과에 따르면 본 시스템은 학생들의 댄스 스킬을 주어진 시간 안에 향상시킬 수 있다.

• Earthquakes and Structures
• /
• 제6권1호
• /
• pp.1-18
• /
• 2014

The main focus of this paper is the analysis of the different components of the variability for strong ground motions recorded from earthquakes produced by the Vrancea subcrustal seismic source. The analysis is performed for two ground motion prediction equations: Youngs et al. (1997) and Zhao et al. (2006), recommended within the SHARE project for the Vrancea subcrustal seismic source and which are proposed in the work of Delavaud et al. (2012) and graded best in Vacareanu et al. (2013c). The first phase of the analysis procedure consists of a grading procedure. In the second phase, the single station sigma procedure is applied for both attenuation models in order to reduce some parts of ground motion models' variability produced by the ergodic assumption. The strong ground motion database which is used throughout the study consists of over 400 accelerograms recorded from 9 Vrancea intermediate-depth seismic events. The results of the single station sigma analysis show significant reduction of the standard deviations, especially in the case of the Youngs et al. (1997) attenuation model, which is also graded better than the other selected GMPE.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권9호
• /
• pp.631-644
• /
• 2002

In this paper efficient algorithms for content-based video retrieval using motion information are proposed, including temporal scale-invariant retrieval and temporal scale-absolute retrieval. In temporal scale-invariant video retrieval, the distance transformation is performed on each trail image in database. Then, from a given que교 trail the pixel values along the query trail are added in each distance image to compute the average distance between the trails of query image and database image, since the intensity of each pixel in distance image represents the distance from that pixel to the nearest edge pixel. For temporal scale-absolute retrieval, a new coding scheme referred to as Motion Retrieval Code is proposed. This code is designed to represent object motions in the human visual sense so that the retrieval performance can be improved. The proposed coding scheme can also achieve a fast matching, since the similarity between two motion vectors can be computed by simple bit operations. The efficiencies of the proposed methods are shown by experimental results.

• 한국컴퓨터정보학회논문지
• /
• 제19권12호
• /
• pp.21-29
• /
• 2014

본 논문에서는 효율적인 로봇공연시스템(RPS:Robot Performance System)을 제안한다. 본 논문에서 제안하는 로봇공연시스템은 외부 음향재생장치의 도움 없이 휴머노이드 로봇 몸체에 개발한 사운드보드를 삽입하여 음향을 재생하고 공연에 필요한 음원을 사운드보드내의 외부기억장치에 기억할 수 있도록 하드웨어를 개발하였다. 또한 공연 기획 시나리오 생성 전문 소프트웨어인 RPPDP(Robot Performance Planning Development Program)를 개발하였는데, RPPDP를 이용하면 기존에 개발된 로봇의 기본동작, 응용동작 및 특별한 상황에 적용되는 동작 등을 모션데이터베이스에서 검색하여 사용할 수 있어서, 적은 비용과 짧은 시간으로 누구나 쉽게 로봇공연을 기획할 수 있도록 하였다.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2006년도 정기 학술대회 논문집
• /
• pp.216-221
• /
• 2006

This study provides a methodology for development of the Seismic Damage Evaluation System (SDES) in Korea. Major systems and status of database related to road networks in Korea are investigated to analyze the usability of the required information for developing the SDES. In this study, the SDES is composed of four components that are the road network component, the ground motion component, the fragile structure component, and the cost component. In addition, the procedures for the construction of database which support the SDES is proposed, and a prototype of the SDES for expressway of Korea is developed based on the developed methodology. The National Geospatial Information System (NGIS) and the National Earthquake Information System (NEIS) are used to develop the road network component and ground motion component, respectively. For the fragile structure component and the cost component, Highway Bridge Management System (HEMS) was used.

• Earthquakes and Structures
• /
• 제10권3호
• /
• pp.563-588
• /
• 2016

In this study, solution models are proposed to obtain code-compatible ground motion record sets which can be used for both uni-directional and bi-directional dynamic analyses. Besides scaled, unscaled ground motion record sets are obtained to show the utility and efficiency of the solution models. For scaled ground motion sets the proposed model is based on hybrid HS-Solver which integrates heuristic harmony search (HS) algorithm with the spreadsheet Solver add-in. For unscaled ground motion sets HS based solution model is proposed. Design spectra defined in Eurocode-8 for different soil types are selected as target spectra. The European Strong Motion Database is used to get ground motion record sets. Also, a sensitivity analysis is conducted to evaluate the effect of different HS solution parameters on the solution accuracy. Results show that the proposed solution models can be regarded as efficient ways to develop scaled and unscaled ground motion sets compatible with code-based design spectra.

• 한국멀티미디어학회논문지
• /
• 제8권5호
• /
• pp.618-632
• /
• 2005

본 논문에서는 모션 캡처 데이터의 효과적인 저장 및 의미 기반 검색을 위한 프레임워크를 제안한다. 모션 캡처 기술은 현실감있는 캐릭터 동작을 얻기 위해 많이 사용되고 있지만, 모션 캡처 데이터의 검색과 저장을 위한 표준화의 부족으로 인한 여러 가지 문제점을 가지고 있다. 또한 미리 캡처된 모션 데이터에 의미론적 부가설명이 없으므로 애니메이터들이 캡처된 모션 데이터로부터 필요한 부분 동작들만을 검색하고 조합하여 새로운 동작을 생성하기가 어렵다. 본 논문의 목적은 모션 캡처 데이터의 재사용성을 향상시키기 위한 것이다 먼저 상이한 모션 캡처 데이터 포맷들을 통합하기 위한 표준 포맷을 제안한다. 제안하는 표준 포맷은 XML 기반의 마크업 언어로서 MCML(Motion Capture Markup Language)라고 한다. 제안하는 MCML은 서로 상이한 포맷들의 변환 또는 통합을 하기 위해 유용할 뿐만 아니라, MCML파일로 모션 데이터 베이스를 구축하므로 모션 캡처 데이터의 재사용성을 향상시킬 수 있다. 또한 모션 캡처 데이터의 부분 동작들에 의미를 부여하고 동작들 사이에 의미론적 연결을 위해 모션 온톨로지를 정의한다. 온톨로지 기반 데이터 접근으로 인해 부분 동작 및 그와 연관된 동작들을 검색하고 항해할 수 있다.

• 한국정보처리학회논문지
• /
• 제7권5호
• /
• pp.1570-1578
• /
• 2000

Object motion is an important feature of content in video sequences. By now, various methods to exact feature about the object motion have been reported[1,2]. However they are not suitable to index video using the motion, since a lot of bits and complex indexing parameters are needed for the indexing [3,4] In this paper, we propose object motion map which could provide efficient indexing method for object motion. The proposed object motion map has both global and local motion information during an object is moving. Furthermore, it requires small bit of memory for the indexing. to evaluate performance of proposed indexing technique, experiments are performed with video database consisting of MPEG-1 video sequence in MPEG-7 test set.