• 한국실내디자인학회논문집
• /
• 제14권2호
• /
• pp.188-196
• /
• 2005

The light has been considered as a main character that can not be omitted in architecture since ancient time. The recognition of space by light means that light makes the fictional space recognizable concretization. Light and shade make emptiness and substance can be easily recognized. Also reiteration and location of light and shade change the degree of acknowledgement. The character of light can strengthen or weaken the power of recognition concerning territory, direction and location. Also it can broaden, close, and segregate the domain and eventually strengthen recognition. In this study, I will try to find how space can be recognized with the help of light in architectural territories in terms of actual states. Also the main aim of my study will be the study of the light application in real space with the architectural example of space recognition by light and possible opportunity of it in space plan.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권11호
• /
• pp.4556-4572
• /
• 2015

Dynamic texture (DT) recognition is a challenging problem in numerous applications. In this study, we propose a new algorithm for DT recognition based on group sparsity structure in conjunction with chaotic feature vector. Bag-of-words model is used to represent each video as a histogram of the chaotic feature vector, which is proposed to capture self-similarity property of the pixel intensity series. The recognition problem is then cast to a group sparsity model, which can be efficiently optimized through alternating direction method of multiplier algorithm. Experimental results show that the proposed method exhibited the best performance among several well-known DT modeling techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.1118-1133
• /
• 2017

Computer vision-based human activity recognition (HAR) has become very famous these days due to its applications in various fields such as smart home healthcare for elderly people. A video-based activity recognition system basically has many goals such as to react based on people's behavior that allows the systems to proactively assist them with their tasks. A novel approach is proposed in this work for depth video based human activity recognition using joint-based motion features of depth body shapes and Deep Belief Network (DBN). From depth video, different body parts of human activities are segmented first by means of a trained random forest. The motion features representing the magnitude and direction of each joint in next frame are extracted. Finally, the features are applied for training a DBN to be used for recognition later. The proposed HAR approach showed superior performance over conventional approaches on private and public datasets, indicating a prominent approach for practical applications in smartly controlled environments.

• 전자공학회논문지B
• /
• 제32B권9호
• /
• pp.1171-1180
• /
• 1995

In this paper, we present a 3-D object recognition system in which the 3-D Hough transform domain is employed to represent the 3-D objects. In object modeling step, the features for recognition are extracted from the CAD models of objects to be recognized. Since the approach is based on the CAD models, the accuracy and flexibility are greatly improved. In matching stage, the sensed image is compared with the stored model, which is assumed to yield a distortion (location and orientation) in the 3-D Hough transform domain. The high dimensional (6-D) parameter space, which defines the distortion, is decomposed into the low dimensional space for an efficient recognition. At first we decompose the distortion parameter into the rotation parameter and the translation parameter, and the rotation parameter is further decomposed into the viewing direction and the rotational angle. Since we use the 3-D Hough transform domain of the input images directly, the sensitivity to the noise and the high computational complexity could be significantly alleviated. The results show that the proposed 3-D object recognition system provides a satisfactory performance on the real range images.

• 융합신호처리학회논문지
• /
• 제5권2호
• /
• pp.119-125
• /
• 2004

방향 성분은 소벨(sobel)과 FFT 방법 등을 주로 사용한다. 소벨을 이용한 방법은 소벨 마스크의 복잡한 처리 과정과 대표 방향 성분을 추출하고자 할 때 픽셀별로 단위 벡터를 만들어 누적시킬 경우 낮은 대비 영상이나 높은 대비 영상이나 같은 값이 나오므로 기울기 크기를 누적할 수 없어 대표 방향을 설정하기 어렵다. FFT를 변환을 이용한 방법은 융선이 정확한 방향 성분을 가지는 경우에만 방향성 추출이 가능하며 별도의 방향 필터를 사용해야 한다. 본 논문에서는 위의 단점을 보완하기 위하여 이진화 된 영상을 세선화 한 후 픽셀 단위로 방향 성분을 추출하며, 8${\times}$8 픽셀크기의 블록 내에 존재하는 픽셀이 가지는 방향 성분 중 가장 많은 방향 성분을 융선의 대표 방향으로 추출하는 새로운 방법을 제안한다.

• 한국생활과학회지
• /
• 제6권2호
• /
• pp.15-26
• /
• 1997

The purpose of this study was to investigate the teacher's and parent's recognition of kindergarten and elementary school about the public education in early childhood education. Especially they included the recognition of concept and necessity, preconsideration, and the direction of future policy of early childhood education to public one. The subjects were 182 teachers and 190 parents in kindergarten and elementary school in Korea. The data was analyzed by Frequency, Percentage, and Chi-Square. The main results were as follows; 1. Teachers and parents defined the concept of public education of the early childhood education as a system which puts a direction in operation and support the finances of national and local government for public and private kindergarten. In addition, teachers and parents thought that the public education was necessary because early childhood was important in developmental aspects. 2. Teachers and parents insisted that the expansion of understanding about public education should be preconsidered and various early childhood programs should be developed. 3. Teachers and parents also agreed that the public education policy should be based on the model and should be progressed sequentially. But they distrusted the current policy.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 추계학술대회
• /
• pp.73-76
• /
• 2013

본 논문은 입 영역의 픽셀 분포의 비교를 통해 혀의 방향 인식 알고리즘을 제안한다. 스마트폰의 크기가 커짐에 따라 얼굴의 제스쳐를 이용한 스마트폰 제어 기술이 요구되고 있다. 처음 코의 영역을 먼저 검출한 뒤 코와 입 부분의 비율로 입의 영역을 검출한다. 입의 영역을 검출한 뒤 방향별 영역을 나누고 혀와 유사한 색의 픽셀분포를 파악해 가리키는 방향을 인지한다. 본 알고리즘은 연구실 연구원 5명을 대상으로 한 실험에서 인식률이 80%에 육박하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1820-1825
• /
• 2004

In this paper, we propose a humanoid active audition system which detects the direction of sound and performs speech recognition using just three microphones. Compared with previous researches, this system comprises simpler algorithm and better amplifier system having advantages to increase a detectible distance of sound signal in spite of simple circuit. In order to verify our system's performance, we install the proposed active audition system to the home service robot, called Hombot II, which has been developed at the KIST (Korea Institute of Science and Technology), thus we confirm excellent performance by experimental results

• 한국정보통신학회논문지
• /
• 제6권7호
• /
• pp.1113-1119
• /
• 2002

본 논문에서는 지문인식 과정의 비용을 줄임으로써 보안유지시스템의 활용범위를 보다 확대시키는 기술응용의 파급효과를 기대하여, 현재 널리 보급된 스캐너 영상입력 장치로 획득된 지문영상처리 과정을 개선하여 보았다. 먼저 영상향상 단계에서는 비교적 양호하다고 이미 알려진 적응적 이진화 기법을 선택하여 이진화 효과를 높였고, 테이블 매핑(Table Mapping)탭을 적용시켜 속도 개선 효과까지 얻을 수 있었다. 또한 이러한 과정을 거쳐 추출된 융선의 방향 특징점들이 지문인식 처리에 유효하게 적용됨을 보였다.

• 한국통신학회논문지
• /
• 제24권8B호
• /
• pp.1500-1505
• /
• 1999

본 논문은 3물체 인식을 위한 깊이정보의 추출을 위해 스테레오 기법의 적용과 기존의 방법론에서 정합횟수에 대한 문제점을 보완하기 위한 물체의 진행 방향 벡터를 이용하는 방법론을 제안한다. 즉, 물체의 진행 방향을 이용하여 진행방향 벡터를 구하고 이를 축으로 회전 이동된 물체를 정합 시킨다. 그리고 Hough변환을 이용하여 얻은 회전 이동에 대응하는 2차원 합성영상을 참조영상으로 설정하고 입력영상과 정합 과정을 수행하였다.