• 한국음향학회지
• /
• 제35권5호
• /
• pp.358-367
• /
• 2016

음원의 위치를 찾는 SSL(Sound Source Localization)은 로봇과의 인터페이스, 화상회의, 스마트 자동차 등 여러 분야에서 꼭 필요한 기술이다. 일반적으로 음원의 위치 정보를 활용하는 기술들은 주로 측정 장치에 대한 음원의 각도 정보를 찾아서 이용하고 있다. 그러나 음원의 위치에 대한 각도를 추정할 때 이용하는 사인 역함수의 비선형적인 특성으로 추정된 각도에 오차가 발생하며, 이에 대한 방안으로 마이크가 담당하는 영역을 분할하는 방법이 제안되었다. 본 논문에서는 마이크 어레이 패턴에 따른 영역분할 방법을 제안하고 음원의 위치를 2차원상의 평면 좌표로 특정하는 방법으로 위치 추정 성능을 평가하였다. 실험에서 잡음에 강인한 GCC-PHAT(Generalized Cross Correlation Phase Transform) 방법을 사용했으며, 마이크 어레이의 패턴은 마이크 3개와 4개로 삼각형과 사각형 두 종류로 구성하였으며, 100개의 음성 데이터로 실험한 결과 실제 환경에서는 3개의 마이크 어레이를 사용해서는 영역 분할 해상도가 낮아서 음원의 위치를 정해진 특정 범위내로 추정하는데 실패했으나, 4개 마이크를 이용하여 해상도를 높였더니 위치추정 성공률이 67 %로 크게 향상됨을 확인할 수 있었다.

• 제어로봇시스템학회논문지
• /
• 제15권5호
• /
• pp.505-510
• /
• 2009

In recent years the space where a robot works has been expanding to the human space unlike traditional industrial robots that work only at fixed positions apart from humans. A human in the recent situation may be the owner of a robot or the target in a robotic application. This paper deals with the latter case; when a robot vision system is employed to monitor humans for a surveillance application, each person in a scene needs to be identified. Humans, however, often move together, and occlusions between them occur frequently. Although this problem has not been seriously tackled in relevant literature, it brings difficulty into later image analysis steps such as tracking and scene understanding. In this paper, a probabilistic neural network is employed to learn the patterns of the best dividing position along the top pixels of an image region of partly occlude people. As this method uses only shape information from an image, it is simple and can be implemented in real time.

• 디지털융복합연구
• /
• 제12권4호
• /
• pp.277-283
• /
• 2014

퍼지모델링은 일반적으로 주어진 데이터를 이용하고 퍼지규칙은 입력변수를 선정하고 각 입력변수에 대한 입력공간을 분할함으로써 입력변수 및 공간분할에 의해 확립된다. 퍼지규칙의 전반부는 입력변수, 공간분할 수 및 소속 함수를 선정하고 본 논문에서 후반부는 선형추론 및 변형된 이차식에 의해 다항식함수의 형태로 나타낸다. 전반부 파라미터의 동정은 입출력 데이터의 최소값과 최대값을 이용하는 최소-최대 방법 및 입출력 데이터를 군집으로 형성하는 C-Means 클러스터링 알고리즘을 사용하여 입력공간을 분할한다. 각 규칙의 후반부 파라미터들, 즉 다항식의 계수들의 동정은 표준최소자승법에 의해 수행된다. 본 논문에서 전반부 소속 함수는 사다리꼴형 멤버쉽 함수를 사용하여 입력공간을 분할하고 비선형공정에서 널리 이용되는 가스로데이터를 사용하여 성능을 평가한다.

• Transactions on Electrical and Electronic Materials
• /
• 제13권1호
• /
• pp.10-15
• /
• 2012

In conventional, skin detection methods using for skin color definitions is based on prior knowledge. By experimentation, the threshold value for dividing the background from the skin region is determined subjectively. A drawback of such techniques is that their performance is dependent on a threshold value which is estimated from repeated experiments. To overcome this, the present paper introduces a skin region detection method. This method uses a histogram approximation based on the mean shift algorithm. This proposed method applies the mean shift procedure to a histogram of a skin map of the input image. It is generated by comparing with the standard skin colors in the $C_bC_r$ color space. It divides the background from the skin region by selecting the maximum value according to the brightness level. As the histogram has the form of a discontinuous function. It is accumulated according to the brightness values of the pixels. It is then, approximated by a Gaussian mixture model (GMM) using the Bezier curve technique. Thus, the proposed method detects the skin region using the mean shift procedure to determine a maximum value. Rather than using a manually selected threshold value, as in existing techniques this becomes the dividing point. Experiments confirm that the new procedure effectively detects the skin region.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 춘계학술대회 학술발표 논문집
• /
• pp.111-114
• /
• 1997

Generally, fuzzy models have the capability of dividing input space into several subspaces. compared to liner ones. But hitherto suggested fuzzy modeling algorithms not take into consideration the correlations between components of sample input data and address them independently of each other, which results in ineffective partition of input space. Therefore, to solve this problem. this letter proposes a new fuzzy modeling algorithm which partitions the input space more efficiently than conventional methods by taking into consideration correlations between components of sample data. As a way to use correlation and divide the input space. the method of principal component is used. Finally, the results of computer simulation are given to demonstrate the validity of this algorithm.

• 전자공학회논문지S
• /
• 제35S권4호
• /
• pp.58-66
• /
• 1998

In many situations, it is very important to identify a certain unkown system, it from its input-output data. For this purpose, several system modeling algorithms have been suggested heretofore, and studies regarding the fuzzy modeling based on its nonlinearity get underway as well. Generatlly, fuzzy models have the capability of dividing input space into several subspaces, compared to linear ones. But hitherto subggested fuzzy modeling algorithms do not take into consideration the correlations between components of sample input data and address them independently of each other, which results in ineffective partition of input space. Therefore, to solve this problem, this letter proposes a new fuzzy modeling algorithm which partitions the input space more efficiently that conventional methods by taking into consideration correlations between components of sample data. As a way to use correlation and divide the input space, the method of principal component is ued. Finally, the results of computer simulation are given to demonstrate the validity of this algorithm.

• 한국실내디자인학회논문집
• /
• 제39호
• /
• pp.124-131
• /
• 2003

The purpose of this study is furnishing applicable data, in deviation from the conventional study of architectural planning, for funeral ceremony hall actually built as a various form. For that, this study performed analysis of condolent space, through dividing space into three phase which is planning unit, organizing unit and making layout as a general method of architectural planning steps. The results are as follows. Establishing spaces for bereaved family's rest in funeral space is also applicable, through the renovation, in case of A type u nit that is more than 25$m^2$. If wish to organize funeral space unit by monolithic space type at planning, than should be controle d size of unit so as not to excessive and if wish to organize by connection style and 1:1 separation style, than area of room where coffin is placed should be considered not overly lacking than condoler's waiting space. On arranging of middle corridor type should be controled scale of funeral space so that is not lacking than room where coffin is placed. In case of hall type, there are necessity to make area of condoler's waiting space do not excess than area of room where coffin is placed.

• KIEAE Journal
• /
• 제12권1호
• /
• pp.35-43
• /
• 2012

Algorithm-based architecture helps specifically dividing the environmental variables of a target space into individual factors to build object-oriented programming, classifying them into an individual object according to the environmental variables of each planning circumstance, and distributing each structure into small structures. In addition, each itemized matter of construction is set as a condition, and thus it is possible to respond to the space condition of various circumstances which occur in the architectural planning process. This study is intended for predicting that a sketch role in the design process can be replaced by a design method utilizing an algorithm, through the external solar radiation and the illuminance value of indoor lighting device among the environmental variables of a target space, and for seeking a way to create a design alternative and improve the design quality by using computer-based algorithm design.

• Smart Structures and Systems
• /
• 제1권3호
• /
• pp.283-308
• /
• 2005

This paper features about the modeling and design of a fast output sampling feedback controller for a smart Timoshenko beam system for a SISO case by considering the first 3 vibratory modes. The beam structure is modeled in state space form using FEM technique and the Timoshenko beam theory by dividing the beam into 4 finite elements and placing the piezoelectric sensor/actuator at one location as a collocated pair, i.e., as surface mounted sensor/actuator, say, at FE position 2. State space models are developed for various aspect ratios by considering the shear effects and the axial displacements. The effects of changing the aspect ratio on the master structure is observed and the performance of the designed FOS controller on the beam system is evaluated for vibration control.

• 인터넷정보학회논문지
• /
• 제19권3호
• /
• pp.43-48
• /
• 2018

본 논문은 DNN(Deep Neural Network)와 슈퍼픽셀을 이용한 실내 공간 인식 알고리즘을 제안한다. 영상으로부터 실내 공간 인식을 위해 우선 영상 분할을 위한 세그멘테이션 프로세스가 필요하다. 이를 위해 본 논문에서는 적당한 크기로 나눌 수 있는 슈퍼 픽셀 알고리즘을 이용해 세그멘테이션을 수행한다. 각 세그먼트를 인식하기 위해 세그먼트마다 제안하는 방법을 이용하여 특징을 추출한다. 추출된 특징들을 DNN을 이용하여 학습하고, 학습으로부터 추출된 DNN모델을 이용하여 각 세그먼트를 인식한다. 실험 결과를 통해 제안하는 방법과 기존의 알고리즘과의 성능 비교 분석을 한다.