• 설비공학논문집
• /
• 제28권2호
• /
• pp.81-88
• /
• 2016

There are many types of national and international standards for low temperature tests depending on the products. This study conducted CFD analysis and estimation of the energy efficiency of the chamber both with and without a test object by considering variations of COP and specific volume according to temperature. The supply air was located in the upper area to compare the cooling performance for each location using various outlets in mixed ventilated conditions. For cases without the test object, the air temperature of the upper supply and center extract on the opposite side type chamber cooled faster than other areas by 4.3~29.8%. However, for cases with the test object, the object temperature of the upper supply and lower extract type chamber cooled faster than the other areas by 7.2~31.5%. The cooling efficiency of the air inside the chamber and the test object did not show the same pattern, which indicates the need to consider the cooling performance by not only the air but also the test object in the cryogenic chamber design for testing.

• 한국정보통신학회논문지
• /
• 제22권7호
• /
• pp.956-962
• /
• 2018

본 논문은 영상에 포함된 객체 특징을 추출하기 위한 연구로서, 말레이시아 산림에서 드론으로 항공 촬영된 산림 영상사진을 이용하여 실제로 산림 속에 존재하는 나무를 파악하기 위한 방법을 기술한다. 일반적으로 회색조 영상특징 추출방법으로는 LBP 방식과 GLCM 방식, Gabor 필터 방식 등이 많이 사용되고 있다. 본 연구에서는 드론으로 촬영된 영상이므로 나뭇잎 질감이 매우 유사하기 때문에, 질감 자체보다는 표본으로 채취한 샘플들에 대한 통계적 특성을 이용한 객체 추출 방식을 제안한다. 이를 위하여 먼저 샘플 영상을 생성하고, 생성된 샘플영상과 원 영상간의 상호상관관계를 이용하여 객체를 검출한다. 각 샘플영상들에 대한 평균치 및 표준편차는 객체 샘플을 분간하고, 판단하기 위한 중요한 자료로 사용될 수 있으며, 또한 RGB 모델과 HSV 모델의 각 신호성분들을 분석하여 객체판단에 유용한 샘플 영상에 대한 통계값을 이용함으로서 객체 추출 확률을 높일 수 있다.

• 제어로봇시스템학회논문지
• /
• 제18권1호
• /
• pp.35-41
• /
• 2012

This paper proposes a moving object detection algorithm for active camera system that can be applied to mobile robot and intelligent surveillance system. Most of moving object detection algorithms based on a stationary camera system. These algorithms used fixed surveillance system that does not consider the motion of the background or robot tracking system that track pre-learned object. Unlike the stationary camera system, the active camera system has a problem that is difficult to extract the moving object due to the error occurred by the movement of camera. In order to overcome this problem, the motion of the camera was compensated by using SURF and Pseudo Perspective model, and then the moving object is extracted efficiently using stochastic Label Cluster transport model. This method is possible to detect moving object because that minimizes effect of the background movement. Our approach proves robust and effective in terms of moving object detection in active camera system.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.535-540
• /
• 2009

Recently, autonomous robots which can achieve the complex tasks have been required with the advance of robotics. Advanced robot vision for recognition is necessary for the realization of such robots. In this paper, we propose a method to recognize an object in the actual environment. We assume that a 3D-object model used in our proposal method is the voxel data. Its inside is full up and its surface has color information. We also define the word "recognition" as the estimation of a target object's condition. This condition means the posture and the position of a target object in the actual environment. The proposal method consists of three steps. In Step 1, we extract features from the 3D-object model. In Step 2, we estimate the position of the target object. At last, we estimate the posture of the target object in Step 3. And we experiment in the actual environment. We also confirm the performance of our proposal method from results.

• 한국정보통신학회논문지
• /
• 제15권11호
• /
• pp.2321-2326
• /
• 2011

경추는 머리와 몸통을 이어주는 중요한 요충지이기 때문에 매우 중요한 기관이며 매우 복잡한 구조로 되어있다. 본 논문에서는 경추 초음파 영상에서 경추 부분에 존재하는 흉쇄유돌근을 자동으로 검출하는 방법을 제안한다. 경추 초음파 영상에서 촬영 정보나 눈금자 등의 필요 없는 부분을 제외한 ROI(Region of Interest)영상을 추출하고 Ends-In Search Stretching 알고리즘을 적용하여 명암 대비를 강조한다. Stretching된 영상에 20 이상의 명암도를 가지는 픽셀을 대상으로 평균 이진화를 적용한 후, 잡음을 제거한다. 잡음이 제거된 영상에 흉쇄유돌근을 둘러싸고 있는 근막의 위치 정보를 이용하여 근막을 추출한 후, 근막의 객체 수에 따라서 각기 다른 방법을 적용하여 근육을 추출한다. 근막 객체가 하나인 경우에는 위에서 아래로 탐색하여 1차 근육 영역을 추출하고, 오른쪽에서 왼쪽으로 탐색하여 2차 근육 영역을 추출한 후, 1차와 2차 근육 영상을 하나로 합쳐 최종 근육 영역을 추출한다. 근막 객체가 두 개인 경우에는 근막 객체의 상단과 하단까지의 영역을 모두 추출한 후, 근막 객체 영역을 제거하는 방법으로 근육 영역을 추출한다. 추출된 근육 영역 중에서 두께가 가장 두꺼운 부분을 근육의 두께로 측정한다. 본 논문에서 제안된 방법을 경추 초음파 영상 30장을 대상으로 실험하여 물리치료사가 분석한 결과, 제안된 방법이 흉쇄유돌근을 정확히 추출되는 것을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.161.5-161
• /
• 2001

Robots are required to assist our activities in daily life. In this paper, we focus on arm movement to catch moving object as one of important tasks frequently performed by human. We propose an algorithm which enables a robot to perform human-like arm motion to catch a moving object. First we analyze human hand trajectories and velocity profiles to catch an object. From the experimental results, we extract some characteristics in the process of approaching and following a moving object and confirm that these are necessary to realize human-like motion. We then adopt an instantaneous optimal control method which evaluates the error and energy cost at each sampling step, and design two time-varying weight matrices to introduce human characteristic into robot motion. The matrix concerning the error is defined as a time-increasing ...

• 디지털산업정보학회논문지
• /
• 제12권4호
• /
• pp.115-121
• /
• 2016

Recently, it has become an important problem to extract semantic objects from videos, which are useful for improving the performance of video compression and video retrieval. In this thesis, an automatic extraction method of moving objects of interest in video is suggested. We define that an moving object of interest should be relatively large in a frame image and should occur frequently in a scene. The moving object of interest should have different motion from camera motion. Moving object of interest are determined through spatial continuity by the AMOS method and moving histogram. Through experiments with diverse scenes, we found that the proposed method extracted almost all of the objects of interest selected by the user but its precision was 69% because of over-extraction.

• 한국컴퓨터정보학회논문지
• /
• 제20권7호
• /
• pp.17-24
• /
• 2015

In this paper, we propose a method to solve ghosting problem. To generate adaptive background, using an exponentially decreasing number of frames, may improve object detection performance. To extract moving objects from the background by using a differential image, detection error may be caused by object rotations or environmental changes. A ghosting problem can be issue-driven when there are outdoor environmental changes and moving objects. We studied that a differential image by adaptive background may reduce the ghosting problem. In experimental results, we test that our method can solve the ghosting problem.

• 한국정보처리학회논문지
• /
• 제7권3호
• /
• pp.818-830
• /
• 2000

Automation tools for program analysis are needed in order to program understand and maintain, extract the characteristics of object-oriented program such as class name, member function and data member. In this paper, we carried out design and implementation of the automation tool for effective maintenance of object-oriented software. Being based on Reverse Engineering, this approach extracts class relationship information from C++ source code and generates object-oriented model of class diagram using UML as the standard object-oriented methodology. Therefore, this paper provides developers visualized including class information, definitions of classes, inheritance relationships, set relationships, and simple reference relationships. Finally in this paper, we propose a method that construct class relationship information to table in analysis state and make form of table construction to link form so tat developers can perform understanding and maintaining program efficiently. And this method enable to restructure and reuse in object-oriented model.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 추계학술발표대회
• /
• pp.1404-1407
• /
• 2013

Mobile phone GPS positioning system is a function we often use, which can make user locate his own position all time. But due to lots of inconvenience brought to us by some error existing in mobile phone positioning system, how to accurately position becomes a hot research topic at home and abroad. This paper puts forward a way of precise calculating position. Firstly, take object's image with mobile phone camera; then, process the image to extract and identify object inside; finally, calculate the distance between the object and user with the object's information stored in the database.