• The KIPS Transactions:PartD
• /
• v.11D no.7 s.96
• /
• pp.1443-1450
• /
• 2004

The clustering characteristics for a number of classes, and defining the inheritance relations between the classes is a difficult and complex problem in an early stage of object oriented software development. We discuss a traditional iterative approach for the reuse of the existing classes in a library and an integrated approach to creating a number of new classes presented in this study. This paper formulates a character-istic clustering problem for zero-one integer programming and presents a network solution method with illustrative examples and the basic rules to define the inheritance relations between the classes. The network solution method for a characteristic clustering problem is based on a distance parameter between every pair of objects with characteristics. We apply the approach to a real problem taken from industry.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.5
• /
• pp.63-71
• /
• 2008

In this paper, we propose a color based hierarchically propagated particle filter that extends the color based particle filter into the articulated upper body tracking. Since color feature is robust to partial occlusion and rotation, the color based particle filter is widely used for object tracking. However, in articulated body tacking, it is not desirable to use the traditional particle filter because the dimension of the state vector usually is high and thus, many samples are required for robust hacking. To overcome this problem, we use a hierarchical tracking method for each body part based on the blown body part. By using a hierarchical tracking method, we can reduce the number of samples for robust tracking in the cluttered environment. Also for human pose recognition, we classify the human pose into eight categories using Support Vector Machine(SVM) according to the angle between upper- arm and fore-arm. Experimental results show that our proposed method is more efficient than the traditional particle filter.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.5 s.43
• /
• pp.115-125
• /
• 2006

A concept hierarchy represents the knowledge with multi-level form, which is very useful to categorize, store and retrieve the data. Traditionally, a concept hierarchy has been built manually by domain experts. However, the manual construction of a concept hierarchy has caused many problems such as enormous development and maintenance costs and human errors such as inconsistency. This paper proposes the automatic creation of concept hierarchies using the predefined hypernym relation. To create the hierarchy automatically, we first eliminate the ambiguity of the senses of data values, and construct the hierarchy by grouping and leveling of the remaining senses. We use the WordNet explanations for multi-meaning word to eliminate the ambiguity and use the WordNet hypernym relations to create multi-level hierarchy structure.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.439-448
• /
• 2021

Driver negligence accounts for the largest proportion of the causes of traffic accidents, and research to detect them is continuously being conducted. This paper proposes a method to accurately detect a distracted driver and localize the most characteristic parts of the driver. The proposed method hierarchically constructs a CNN basic model that classifies 10 classes based on CAM in order to detect driver distration and 4 subclass models for detailed classification of classes having a confusing or common feature area in this model. The classification result output from each model can be considered as a new feature indicating the degree of matching with the CNN feature maps, and the accuracy of classification is improved by horizontally combining and learning them. In addition, by combining the heat map results reflecting the classification results of the basic and detailed classification models, the characteristic areas of attention in the image are found. The proposed method obtained an accuracy of 95.14% in an experiment using the State Farm data set, which is 2.94% higher than the 92.2%, which is the highest accuracy among the results using this data set. Also, it was confirmed by the experiment that more meaningful and accurate attention areas were found than the results of the attention area found when only the basic model was used.

• Journal of Broadcast Engineering
• /
• v.12 no.6
• /
• pp.596-610
• /
• 2007

In order to reduce the complexity of SVC encoding, we introduce a fast mode decision method in the enhancement layers of spatial scalability by selectively performing the inter-layer residual prediction of SVC. The Inter-layer residual prediction coding in Scalable Video Coding has a large advantage of enhancing the coding efficiency since it utilizes the correlation between two residuals from a lower spatial layer and its next higher spatial layer. However, this entails the dramatical increase in the complexity of SVC encoders. The proposed method is to analyze the characteristics of integer transform coefficients for the subtracted signal for two residuals from lower and upper spatial layers. Then it selectively performs the inter-layer residual prediction coding and rate-distortion optimizations in the upper spatial enhancement layer if the SAD values of residuals exceed adaptive threshold values. Therefore, by classifying the residuals according to the properties of integer-transform coefficients only with SAD of residuals between two layers, the SVC encoder can perform the inter-layer residual coding selectively, thus significantly reducing the total required encoding time. The proposed method results in reduction of the total encoding time with 51.5% in average while maintaining the RD performance with negligible amounts of quality degradation.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.493-503
• /
• 2014

A hierarchical classification scheme, which can reduce the spectral ambiguity and also reflect crop cultivation patterns from past land-cover maps, is presented for the purpose of the early production of crop classification maps in large-scale crop areas. Specifically, the effects of mixed pixels are minimized not only by applying a hierarchical classification approach based on different spectral characteristics from crop growth cycles, but also by considering temporal contextual information derived from past crop cultivation patterns. The applicability of the presented classification scheme was evaluated by a case study of Iowa State in USA with time-series MODIS 250 m Normalized Difference Vegetation Index(NDVI) data sets and past Cropland Data Layers(CDLs). Corn and soybean, which are major crop types in the study area and also display spectral similarity, could be properly classified by applying different classification stages and accounting for past crop cultivation patterns. The classification result by the presented scheme showed increases of minimum 7.68%p and maximum 20.96%p in overall accuracy, compared with one based on purely spectral information. In addition, the combination of temporal contextual information during classification was less affected by the number of NDVI data sets and the best overall accuracy of 86.63% was achieved. Thus, it is expected that this classification scheme can be effectively used for the early production of large-area crop classification maps in major feed-grain importing countries.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.2
• /
• pp.98-98
• /
• 2013

태양의 활동영역에서 관측할 수 있는 흑점은 주로 흑점군으로 관측되며, 태양폭발현상의 발생을 예보하기 위한 중요한 관측 대상 중 하나이다. 현재 태양 폭발을 예보하는 모델들은 McIntosh 흑점군 분류법을 사용하며 통계적 모델과 기계학습 모델로 나누어진다. 컴퓨터는 흑점군의 형태학적 특성을 연속적인 값으로 계산하지만 흑점군의 형태적 다양성으로 인해 McIntosh 분류법과 일치하지 않는 경우가 있다. 이러한 이유로 컴퓨터가 계산한 흑점군의 형태학적인 특성을 예보에 직접 적용하는 것이 필요하다. 우리는 흑점군을 검출하기 위해 최소신장트리(Minimum spanning tree : MST)를 이용한 계층적 군집화 기법을 수행하였다. 그래프(Graph)이론에서 최소신장트리는 정점(Vertex)과 간선(Edge)으로 구성된 간선의 가중치의 합이 최소인 트리이다. 우리는 모든 흑점을 정점, 그들의 연결을 간선으로 적용하여 최소신장트리를 작성하였다. 또한 최소신장트리를 활용한 계층적 군집화기법은 초기값에 따른 군집화 결과의 차이가 없기 때문에 흑점군 검출에 있어서 가장 적합한 알고리즘이다. 이를 통해 흑점군의 기본적인 형태학적인 특성(개수, 면적, 면적비 등)을 계산하고 최소신장트리를 통해 가장 면적이 큰 흑점을 중심으로 트리의 깊이(Depth)와 차수(Degree)를 계산하였다. 이 방법을 2003년 SOHO/MDI의 태양 가시광 영상에 적용하여 구한 흑점군의 내부 흑점수와 면적은 NOAA에서 산출한 값들과 각각 90%, 99%의 좋은 상관관계를 가졌다. 우리는 이 연구를 통해 흑점군의 형태학적인 특성과 더불어 예보에 직접적으로 활용할 수 있는 방법을 논의하고자 한다.

• Journal of Korea Multimedia Society
• /
• v.11 no.5
• /
• pp.710-727
• /
• 2008

Service-oriented computing systems have been issued by their properties of reducing software development time and effort by reusing functional service units. The reusability of services can effectively promote through loose coupling between services. But strong associations of object-oriented systems such as inheritance and aggregation create a rather tight coupling between objects. The component-based systems without inheritance and aggregation create a loose coupling between components. Thus components provide service realization at runtime using the functionality provided by their interfaces. Therefore legacy component-based systems need to have service-oriented computing concept in order to support functional service units efficiently. Also, conventional methods for service-oriented computing system have not suggested the clear classification of service layers, the clear service identification guideline introducing service layers and a service mapping method between serviceces of each layer. Therefore we suggest the service classification and the identification guideline of business view and implementation view introducing layers and propose a mapping between two views. That is, we research service layers, service identification, diversified service sizes and a service mapping method between services of each layer. This can be applied to legacy component-based system to extend to the service-oriented computing system.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.510-520
• /
• 2000

For content-based video indexing and retrieval, it is necessary to segment video data into video shots and then select key frames or representative frames for each shot. However, it is very difficult to select key frames automatically because the task of selecting meaningful frames is quite subjective. In this paper, we propose a new approach in selecting key frames based on visual contents such as region information and their temporal variations in the shot. First of all, we classify video shots into panning shots, zooming shots, tilting shots or no camera motion shots by detecting camera motion information in video shots. Then, in each category, we apply appropriate fuzzy rules to select key frames based on meaningful content in frame. Finally, we control the number of key frames in the selection process by adjusting the degree of detail in representing video shots.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.76-78
• /
• 2006

인간의 주관적이고 애매한 감성은 차세대 컴퓨팅의 다양한 분야에서 연구되며. 인간의 감성을 이해하고 감성의 변화에 능동적으로 반응하는 사용자 중심의 정보 처리에 대한 요구가 급격히 증가하고 있다. 우리는 감성기반 이미지 검색을 위해 저차원 시각정보에 대한 강성처리를 연구하고 있다. 기존의 저차원 시각정보 특징을 고려한 내용기반 이미지 검색 방법은 사용자의 취향이나 감성 요구에 적합한 결과를 검색하기에는 많은 어려움이 있다. 본 논문에서는 인간의 감성을 이해, 검색, 인식하기 위한 시각정보와 감성간의 관계 연구 중 우리의 기존 연구인 시각적 형태 정보의 감성어휘 공간에서 형태와 어휘간의 감성거리를 이용한 분류방법을 제안한다. 그리고 분류된 각 영역에서의 대표 어휘를 추출하여 시각적 형태에 따른 감성어휘간의 구체적 계층 관계를 정의한다. 이는 감성기반 이미지 검색 분야에 활용 가능한 연구이며, 우리가 사용하는 언어에 내재된 감성정보를 해석하고 그 어휘들의 체계적인 시각적 감성관계를 정의하는 의의를 갖는다.