• ETRI Journal
• /
• v.27 no.6
• /
• pp.713-724
• /
• 2005

This paper focuses on the problem of key-frames coding and proposes a new promising approach based on the use of fractals. The summary, made of a set of key-frames selected from a full-length video sequence, is coded by using a 3D fractal scheme. This allows the video presentation tool to expand the video sequence in a "natural" way by using the property of the fractals to reproduce the signal at several resolutions. This feature represents an important novelty of this work with respect to the alternative approaches, which mainly focus on the compression ratio without taking into account the presentation aspect of the video summary. In devising the coding scheme, we have taken care of the computational complexity inherent in fractal coding. Accordingly, the key-frames are first wavelet transformed, and the fractal coding is then applied to each subband to reduce the search range. Experimental results show the effectiveness of the proposed approach.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.156-156
• /
• 2002

We apply independent component analysis (ICA) for extracting an optimal basis to the problem of finding efficient features for representing speech signals of a given speaker The speech segments are assumed to be generated by a linear combination of the basis functions, thus the distribution of speech segments of a speaker is modeled by adapting the basis functions so that each source component is statistically independent. The learned basis functions are oriented and localized in both space and frequency, bearing a resemblance to Gabor wavelets. These features are speaker dependent characteristics and to assess their efficiency we performed speaker identification experiments and compared our results with the conventional Fourier-basis. Our results show that the proposed method is more efficient than the conventional Fourier-based features in that they can obtain a higher speaker identification rate.

• Proceedings of the KSR Conference
• /
• 2006.11b
• /
• pp.947-953
• /
• 2006

ATC on-board equipment require realtime embedded software with high level of safety and reliability. To satisfy these requirements, many techniques are applied to the development of software during the lifecycle. In case of software modeling, object-oriented methodology is widening its niche replacing traditional structured methodology and modeling in UML using a CASE tool is a growing trend. In this paper, we modeled ATC on-board software in UML using Rhapsody, which is a modeling tool for realtime embedded software. We modeled the behavior of ATC on-board equipment based on state machine diagram and validated the model using the animation feature provided in the tool. According to our study, the CASE tool based on UML showed high level of applicability in modeling and verifying the software with complex behavioral characteristics.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1092-1099
• /
• 2017

This paper proposes a novel way of vehicle detection and classification based on image features. There are two main processes in the proposed system, which are database construction and vehicle classification processes. In the database construction, there is a tight censorship for choosing appropriate images of the training set under the rigorous standard. These images are trained using Haar features for vehicle detection and histogram of oriented gradients extraction for vehicle classification based on the support vector machine. Additionally, in the vehicle detection and classification processes, the region of interest is reset using a number plate to reduce complexity. In the experimental results, the proposed system had the accuracy of 0.9776 and the $F_1$ score of 0.9327 for vehicle classification.

• Annual Conference of KIPS
• /
• 2003.11c
• /
• pp.1579-1582
• /
• 2003

본 연구는 컴포넌트 검색을 위해서 컴포넌트를 컨덱스트에 의해 패싯 분류하고, 컨텍스트와 특성들간의 관련값에 대한 통계적 분석에 의해 시소러스를 구축하여 다중 패싯 분류된 컴포넌트를 효율적으로 검색할 수 있는 방법을 제안하였다. 소스 코드로부터 추출된 특성은 카이제곱 방법을 통하여 간소화가 이루어지며, E-SARM 방법을 사용하여 컨텍스트의 자동 검색이 이루어질 수 있도록 하였다. 쿼리에 대해 자동 검색된 컨덱스트에 의해 후보 컴포넌트가 선정되고, 쿼리와 컴포넌트 간의 유사도가 계산됨으로써 컴포넌트가 검색될 수 있도록 하였다. 본 연구는 다중 패싯 분류된 컴포넌트의 검색에 효율적이며, 컴포넌트의 재사용성을 높일 수 있도록 하였다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.5 s.23
• /
• pp.17-28
• /
• 2002

Time is regarded as an essential feature of land information enabling to track historical landmarks of land uses, ownerships, and taxations based on cadastral maps. Object-oriented temporal modeling helps to simulate and imitate time-varying cadastral data in a chronological and persistent manner. The aim of study is to analyze the role of temporal cadastre tracing footprints of foregoing events in response to various needs and demands associated with historical information of cadastral transactions. In this paper, temporal cadastral object model (TCOM) is proposed to delineate object version history. As an evidence of a new approach and conceptual idea for the importance of temporal cadastre, a part of spatio-temporal processes is illustrated to explain major changes of cadastral map. The feasibility and application of the approach is confirmed by proof-of-concept of temporal cadastre in land information management.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.645-647
• /
• 2003

In this work a new method for on-line scene segmentation is developed. In remote sensing a scene is represented by the pixel-oriented features. It is possible to reduce data redundancy by an unsupervised segment-feature extraction process, where the segment-features, rather than the pixelfeatures, are used for multispectral scene representation. The algorithm partitions the observation space into exhaustive set of disjoint segments. Then, pixels belonging to each segment are characterized by segment features. Illustrative examples are presented, and the performance of features is investigated. Results show an average compression more than 25, the classification performance is improved for all classes, and the CPU time required for classification is reduced by the same factor.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.44-49
• /
• 2007

새로운 패러다임인 유비쿼터스에 대한 개념이나 적용 기술들에 대해서는 많은 연구가 진행되고 있으나, 이를 고려한 도메인 분석 기법에 대한 연구는 많지 않다. 또한, 범용적으로 사용되고 있는 휘처 기반의 도메인 분석 기법은 공간 재설계나 상황 인지 등의 유비쿼터스 컴퓨팅의 대표적인 특징을 수용하는 데에는 한계를 가지고 있다. 본 논문에서는 #공간 재설계#나 #상황 인지#에 초점을 두고 휘처 개발 방법을 통해 유비쿼터스 컴퓨팅 서비스의 도메인 분석 방법을 제시한다. 유비쿼터스 환경을 위한 정형화된 유비쿼터스 휘처 메타모델을 제시하고, 유비쿼터스 컴퓨팅 서비스를 휘처로 표현함으로써 기존의 휘처 모델링 방법에 의한 유비쿼터스 컴퓨팅 서비스의 모델링 접근을 가능하게 한다. 이로써 유비쿼터스 서비스 도메인 모델의 효과적인 분석을 가능하게 하고 정형화된 휘처 모델을 통한 기존 휘처 모델의 제품 계열 개발에 따른 재사용성을 증진시킬 수 있다.

• Cross-Cultural Studies
• /
• v.26
• /
• pp.227-248
• /
• 2012

Orchid Dream Wonderful Biography(蘭花夢奇傳), whose author was Yimmeishanren(吟梅山人), is a Xia-Yi-Ai-Qing(俠義愛情) novel in the late Qing Dynasty. The work published in 1905 when Emperor Guangxu(光緖) governed China. The novel was reprinted for several times to its excellent art feature as well as its public praise. Orchid Dream Wonderful Biography narratives the life story of the heroin, Songbaozhu(松寶珠). Songbaozhu disguises herself as a man, takes the imperial examination, and takes part in the war. However, she is abused after marring Xuwenqing(許文卿), finally, she dies in misery. Songbaozhu's tragic fate show that although a woman may disguise as a man and makes great contributions in novel, it would never come true in reality. Songbaolin(松寶林) is also home to female hero. She has a younger brother and sister were strictly education. She is a female hero of the pitch. The writer creates her, had to satisfy a social reality male. Orchid Dream Wonderful Biography, this work has had a tragic or a reality. This work represents the limits of consciousness and the writers. Orchid Dream Wonderful Biography did not transcend male-oriented notions.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.5
• /
• pp.11-17
• /
• 2019

In this study, we propose an ensemble engine, which is a framework for game engine optimized for visual novels genre, focusing on storytelling among various game genres. The game of Visual Nobel genre is based on multi-ending story and features branching of various scenarios according to user's choice. The proposed engine supports various multi-scenarios and multi-endings based on nodes according to the characteristics of these genres. In addition, it provides a convenient and intuitive user interface that not only enhances user immersion but also provides VR function to maximize the sense of presence. We will demonstrate the usefulness of the proposed game engine by designing the framework of a game engine suitable for this feature and actually creating variety stories automatically.