• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 추계학술대회
• /
• pp.995-998
• /
• 2013

본 논문에서는 자기 조직화 기능을 갖는 Kohonen의 SOM(Self Organization Map) 신경회로망에 2단계의 학습과정을 활용하여 항공영상에서 물체를 인근의 물체와 효과적으로 구별하기 위한 접근방법을 제안하고 실제의 항공영상에 적용하여 기존의 고전적인 K-means 알고리즘 및 원래의 SOM 알고리즘보다 우수함을 보인다.

• 제어로봇시스템학회논문지
• /
• 제12권4호
• /
• pp.389-394
• /
• 2006

Inaccurate localization exposes a robot to many dangerous conditions. It could make a robot be moved to wrong direction or damaged by collision with surrounding obstacles. There are numerous approaches to self-localization, and there are different modalities as well (vision, laser range finders, ultrasonic sonars). Since sensor information is generally uncertain and contains noise, there are many researches to reduce the noise. But, the correctness is limited because most researches are based on statistical approach. The goal of our research is to measure more exact robot location by matching between built VRML 3D model and real vision image. To determine the position of mobile robot, landmark-localization technique has been applied. Landmarks are any detectable structure in the physical environment. Some use vertical lines, others use specially designed markers, In this paper, specially designed markers are used as landmarks. Given known focal length and a single image of three landmarks it is possible to compute the angular separation between the lines of sight of the landmarks. The image-processing and neural network pattern matching techniques are employed to recognize landmarks placed in a robot working environment. After self-localization, the 2D scene of the vision is overlaid with the VRML scene.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.318-320
• /
• 2006

Inaccurate localization exposes a robot to many dangerous conditions. It could make a robot be moved to wrong direction or damaged by collision with surrounding obstacles. There are numerous approaches to self-localization, and there are different modalities as well (vision, laser range finders, ultrasonic sonars). Since sensor information is generally uncertain and contains noise, there are many researches to reduce the noise. But, the correctness is limited because most researches are based on statistical approach. The goal of our research is to measure more exact robot location by matching between built VRML 3D model and real vision image. To determine the position of mobile robot, landmark-localitzation technique has been applied. Landmarks are any detectable structure in the physical environment. Some use vertical lines, others use specially designed markers, In this paper, specially designed markers are used as landmarks. Given known focal length and a single image of three landmarks it is possible to compute the angular separation between the lines of sight of the landmarks. The image-processing and neural network pattern matching techniques are employed to recognize landmarks placed in a robot working environment. After self-localization, the 2D scene of the vision is overlaid with the VRML scene.

• 자연과학논문집
• /
• 제10권1호
• /
• pp.133-140
• /
• 1998

본 연구는 24항목의 신체계측치와 계산치를 통해서 살펴본 실제체형과 피험자가 인지하고 있는 체형과 비교하기 위하여 비만도에 의해 세 집단으로 분류된 85명의 피험자를 대상으로 신체계측과 설문지조사를 행하였다. 그 결과 다음과 같은 결론을 얻을 수 있었다. 첫째, 의복구매시 사이즈와 관련된 둘레항목에서의 자각적 인지체형은 실제체형과 같은 경향으로 인식하고 있었다. 둘째, 자각적 인지체형 항목 중 구체적인 정보가 제공되지 않은 키, 비만도, 다리길이 등의 항목은 피험자가 선호하는 이상적 이미지와 관련되어 평가되었다.

• 재활복지공학회논문지
• /
• 제11권4호
• /
• pp.331-338
• /
• 2017

본 연구에서는 포터블 형 X-ray 발생장치를 제작하였고, 제작된 발생장치로부터 영상증배관을 이용하여 실시간 영상획득시스템 구축하였다. 획득된 영상으로부터 인공관절 위치가 초기 영상과 차이가 있는지를 검증할 수 있는 실시간 위치오차검증 시스템을 개발하였다. 패턴 매칭 기법을 이용하여 간단히 기준영상에서 관심영역 부위의 템플릿영상을 추출하여 비교하고 싶은 비교영상과 비교하여 본 결과 500-1000점 사이의 유사도를 수치로 표시하여 유사정도를 알 수 있었고, x, y 위치와 차이가 나는 각도를 표시해 줌으로써 실시간 위치오차검증이 가능함을 알 수 있었다. 본 시스템은 포터블형이며, 자체 차폐시설을 갖추고 있다. 조사장치의 출력도 1kw의 소형으로 제작되어 이동형으로 사용할 수 있으며, 산업용의 비파괴분야 및 의료기관이 없는 외진 곳에서 발생된 응급환자의 경우 손, 발과 같은 작은 부위의 진단용 분야 등에 활용할 수 있는 유효성을 보여주었다.

• 한국의류학회지
• /
• 제41권1호
• /
• pp.1-16
• /
• 2017

This study conducted in-depth interviews with twelve men in their twenties and employed the Zaltman Metaphor Elicitation Technique (ZMET) to identify the ideal self-image and fantasy of men wearing makeup. The results are as follows. First, the ideal self-images of men wearing makeup can be divided into 7 images (well-managed, dissimilar from real identity, masculine, neat, stylish, standing out, and formal). Men who wear makeup pursued an alternative decent image that is different from their reality. They want to be manly, attractive, decorous, and eye-catching through a better looking face. Second, men who wear makeup have insecurities about their looks and personalities that creates dissatisfaction with reality and a desire for a different idealistic self. Makeup was the tool to create the other entity. Makeup facilitated a fantasy of becoming another to gain increased confidence in social relationships. However, without makeup, they showed a lack of confidence and became intimidated that made them even further dependent on makeup. Third, the process helped participants complete a consensus map that represented the emotional and reasoning structures of men wearing makeup. This study showed 7 ideal self-images of men wearing makeup with a fantasy to create a desired ideal self by wearing makeup. The study can be applied to marketing strategy for men's cosmetics and plates' designs.

• Journal of information and communication convergence engineering
• /
• 제12권2호
• /
• pp.128-134
• /
• 2014

In this paper, we present a graphics processing unit (GPU)-based matching technique for the purpose of fast feature matching between different images. The scale invariant feature transform algorithm developed by Lowe for various feature matching applications, such as stereo vision and object recognition, is computationally intensive. To address this problem, we propose a matching technique optimized for GPUs to perform computations in less time. We optimize GPUs for fast computation of keypoints to make our system quick and efficient. The proposed method uses a self-organizing map feature matching technique to perform efficient matching between the different images. The experiments are performed on various image sets to examine the performance of the system under varying conditions, such as image rotation, scaling, and blurring. The experimental results show that the proposed algorithm outperforms the existing feature matching methods, resulting in fast feature matching due to the optimization of the GPU.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.984-989
• /
• 1991

In this paper, a novel type of a visual servoing method is proposed for eye-in-hand robots by employing a self-organizing fuzzy controller. For this is there defined a new Jacobian riot to be the function of a relative position of the object but to be a function of the only image features. Instead of obtaining an analytic form of the proposed Jacobian, a self-organizing fuzzy controller is then proposed to alleviate difficulties in real-time implementation. To show the validities, the proposed method is applied to a 2-dimensional visual servoing task.

• Journal of Positioning, Navigation, and Timing
• /
• 제9권2호
• /
• pp.131-138
• /
• 2020

In this paper, we analyze the delay phenomenon that can occur when controlling an unmanned aerial vehicle using a camera and describe a solution to solve the phenomenon. The group of pictures (GOP) value is changed in order to reduce the delay according to the frame data size that can occur in the moving image data transmission. The appropriate GOP values were determined through experimental data accumulation and validated through camera self-test, system integration laboratory (SIL) verification test and system integration test.

• KIEAE Journal
• /
• 제14권4호
• /
• pp.5-10
• /
• 2014

Since construction work is an indispensable part of daily lives, complaints of noise are unavoidable. Noise control in construction sites is normally known as a regulation by a government and self-motivated noise controls rarely occur. In this paper, a marketing strategy is proposed to provide a potential value of noise control for real estate developer. First, people's perception to construction noise was examined in means of collecting and analyzing media reports between 2005 to 2011. Then decibel test was done in order to test noise generated by different devices in a construction site in various distances. According to the theory of core competency, a conceptual model was raised to illustrate profit and loss situation of the real estate developers in the case they invest more in noise control. The construction noise is discussed that it will ruin people's perception to the company's brand image and reputation. Also, the investment in the creation of silent site is discussed that it will not only bring benefit to the brand image work but also have value of profit in the market.