http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
백승호(Seung-Ho Baeg),박재한(Jae-Han Park),백문홍(Moon-Hong Baeg) 대한전자공학회 2007 대한전자공학회 학술대회 Vol.2007 No.7
This paper is concerned with development of smart objects which are continuously working to help achievements of service robots. Among the functionalities that a home service robot must have are localization, navigation, object recognition, and object handling. These operations are usually performed by a service robot itself and the robot could have performed the given tasks in a limited environment or showed the limited capabilities in a natural environment. We initiated a smart environment project for light weight service robots to provide reliable services by interacting with the environment through the wireless sensor networks. In this paper, we presents our some smart objects which are developed for assisting service robots to achieve useful home service in the smart environment.
이충석 ( Lee Chung Seog ),백승호 ( Baeg Seung Ho ),조용욱 ( Jo Yong Ug ),오도연 ( O Do Yeon ),김현태 ( Kim Hyeon Tae ),김용훈 ( Kim Yong Hun ),김선주 ( Kim Seon Ju ) 대한내과학회 1993 대한내과학회지 Vol.44 No.1
Pulmonary arteriovenous fistula (AVF) is a rare congenital condition originated from malformation of capillary development. Dyspnea, hemoptysis, cyuanosis, hemothorax, and severe neurologic complaints may occur because of the dircet entry of unoxygenated, desaturated arterial blood in to the pulmonary venous system, But, most of patients are asymptomatic. The pathogenesis of AVF is incomplete formation of the vascular septae that separate the arterial and venous plexus that anastomose during fetal life. It can occur either as an isolated process or in association with similar abnormalitities of the skin, mucous membrane, hereditary hemorrhagic telangiectasia (Osler-Weber-Rendu syndrome). Recently we experienced a case of the pulmonary arteriovenous fistula which was detected on simple chest x-ray in 56-year-old asymptomatic woman. There was no abnormal connection between fistula and systemic circulation. The confirmative diagnosis of pulmonary AVF was established by pulmonary angiography. Our case was not performed operation due to symptom free and no change of hemodynamic changes.
다중 위치센서 및 의미론적 지도 기반 로봇의 광역 자기위치인식 방법
박재한(Jae-Han Park),원대희(Dae-Hee Won),백승호(Seung-Ho Baeg),백문홍(Moon-Hong Baeg) 대한전자공학회 2007 대한전자공학회 학술대회 Vol.2007 No.7
This paper presents a noble method of wide area localization for intelligent robots based on multiple location sensors and semantic maps. Although localization is one of important functionalities for service robots, it still has many difficulties because the real environment where robots should works is so complex and dynamical. In our configurations, the robot can receive his position information from location sensors through sensor networks, and it can eliminate the accumulated localization errors. In addition, with the semantic map information the robot can select proper location sensor among multiple sensors at the current position, and connect to the proper location sensor automatically. The feasibility of our approaches was confirmed by testing results in real environments.
이미지의 주요 색상 정보들을 이용한 실시간 객체 검출 방법
박재한 ( Kyung-wook Park ),고재한 ( Jaehan Koh ),박경욱 ( Jae-han Park ),백승호 ( Seung-ho Baeg ),백문홍 ( Moon-hong Baeg ) 한국정보처리학회 2007 한국정보처리학회 학술대회논문집 Vol.14 No.1
자동으로 이미지 안에 존재하는 객체들을 인식하는 문제는 내용 기반 이미지 검색이나 로봇 비전과 같은 다양한 분야들에서 매우 중요한 문제이다. 이 문제를 해결하기 위하여 본 논문에서는 객체의 주요 색상 정보들을 이용하여 실시간으로 이미지 안의 객체들을 인식하는 알고리즘을 제안한다. 본 논문에서 제안하는 방법의 전체적인 구조는 다음과 같다. 처음에 MPEG-7 색상 정보 기술자들 중 하나인 주요 색상 정보 기술자를 이용하여 객체의 주요 색상 정보들을 추출한다. 이 때 이 정보는 가우시안 색상 모델링을 통하여 빛이나 그림자와 같은 외부 환경 조건에 좀 더 강인한 색상 정보로 변환된다. 다음으로 변환된 색상 정보들을 기반으로 주요 객체와 입력 이미지와의 픽셀 값 차이를 계산하고, 임계값 이상의 값을 가지는 픽셀들을 제거한다. 마지막으로 입력 이미지에서 제거되지 않은 픽셀들을 기반으로 하나의 영역을 생성한다. 결론으로서, 본 논문에서는 제안된 방법에 대한 실험 평가들을 수행 및 분석하고 몇몇 한계점들에 대해서 알아본다. 또한 이 문제들을 해결하기 위한 앞으로의 연구 계획에 대해서 기술한다.
서비스 로봇 환경에서의 조명 영향에 강인한 시각 서술자 기반 물체인식 방법
박재한(Jae-Han Park),고재한(Jaehan Koh),박경욱(Kyung-Wook Park),백승호(Seung-Ho Baeg),백문홍(Moon-Hong Baeg) 대한전자공학회 2007 대한전자공학회 학술대회 Vol.2007 No.7
Recognizing objects of a robot reliably from camera images in a natural environment has been one of the crucial challenges in robot vision. To identify objects from robot camera, we propose an object recognition algorithm on the basis of visual descriptors. The algorithm works robustly under various constraints such as different lighting conditions and the different distances between the robot and the target object. Our object recognition process consists of the following steps. Firstly, Dominant color information is extracted by using Dominant Color Descriptor(DCD) of MPEG-7 standard. Color information is transformed through Gaussian Color Model to minimize the external environmental effects on the image including lighting. Then, after the color transformation, the robot calculates the distance between the target and itself with the dominant color information downloaded from the object description database and the camera images, the filter out pixels having values greater than a threshold. A region of interest is formed after a distance threshold is satisfied. To evaluate the performance of our algorithm, experiments are conducted with six beverage cans that are typical of real-world objects.