• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(2)
• /
• pp.113-116
• /
• 2001

In this paper we present a new hierarchical layout object extraction algorithm, which is based on rectangles rather than edges. The original layout data is modeled as instances connected by wires. Each polygon shape is divided into a set of rectangles and the instances and wires are extracted and recognized from those rectangles together with their connection and size information. We have applied the algorithm to actual layouts. Experiments on several standard cell library demonstrate the effectiveness of the algorithm.

• 정보처리학회논문지B
• /
• 제12B권6호
• /
• pp.671-678
• /
• 2005

본 논문에서는 동영상에서 주요 객체를 추출하여 기존의 배경을 임의의 배경으로 교체하는 알고리즘을 제안한다. 제안된 기법은 이동 통신 화상전화기 및 영상전달 시스템등을 사용한 화상 전송함시 개인의 프라이버시를 보호하고, 배경을 제거함으로써 실제 전송할 데이터의 양을 줄일 수도 있을 뿐만 아니라, 현재배경을 임의의 배경으로 바꾸는 등의 여러 용도로 사용가능하다. 영상처리는 대용량의 데이터를 처리하기 때문에 많은 메모리와 시간 등의 자원을 사용하게 된다. 이는 특히 자원이 제한된 이동통신기기에서 문제가 된다. 실험에서 일반적으로 주요 객체의 움직임의 범위가 크지 않다는 점에 근거하여 검색의 범위를 이전 윤곽선정보의 주변으로 제한함으로써 영상처리에서 걸리는 시간과 자원을 줄일 수 있었다. 구체적으로는 동영상의 초기영상에서 윤곽선 정보를 이용하여 후보 객체영역을 추출하였고, 추출한 영역을 기준으로 다음 영상과 현재 영상과의 차영상을 구하여 움직이는 객체를 추적하는데 이용하였으며, 선택된 영역에서 윤곽선을 구하여 객체영역을 찾는데 이용하였다 이를 통하여 주요 객체와 배경을 효율적으로 분리할 수 있었으며, 사용자가 선택한 임의의 배경으로 대체할 수 있었다.

• 한국의류학회지
• /
• 제25권2호
• /
• pp.315-326
• /
• 2001

This study is to suggest data for setting school uniform size with the size satisfaction degree through finding out the physical body change and uniform size problems following an increase in age during middle school girl days. For this purpose, by analyzing the physical body size data of 13~15 age of girls among $\ulcorner$human body size data of the youth for product design$\lrcorner$publicized under sponsorship of National Technology Quality Institute in 1999 the physical body size change by part following an increase in age during middle school girl days was found out and the most frequent physical body size by grade was suggested. Questionnaire about uniform production status and product size at the object of uniform makers were measured directly, a school uniform wearing status and size satisfaction degree by part were at the abject of middle school girls were examined by means of questionnaire and unsatisfactory factors in uniform size were found out. Based on collected data the most optimum product size in each part by item were suggested. The method of suggesting the most optimum size suitability by item was decided based on the result of survey into corresponding title and product size by maker and that of survey into the size satisfaction degree of middle school girls by maker, and the product size of maker showing the highest size satisfaction degree was selected as the most optimum product size.

• 대한한의진단학회지
• /
• 제16권3호
• /
• pp.41-48
• /
• 2012

Objectives: The aims of this study are to design a optimized mechanical structure of digital tongue imaging system (DTIS) equipped with LEDs in aspects of object distance and camera angle of coverage. Methods and Results: We tried to find optimized object distance while recording a rectangular object of common tongue size. In case object distance is 22 cm or less, edge of the rectangle was not taken beyond the shooting range. In contrast, if object distance is 40 cm or more, the rectangle image was too small. Therefore when considering the variation of subjects, we selected distance of 35-40 cm as appropriate object distance for the DTIS. We also tried to find optimized angle between camera view axis and horizontal line. We photographed from the side of the face of 7 adults with exposed tongue. We drew an exposed tongue lines to connect the tongue tip points and the tongue root points by using the photos acquired from the side faces. And then we calculated the tongue exposure angles between the vertical line and the exposed tongue lines. Mean tongue exposure angle was $28.3^{\circ}$ when tongue was lightly exposed and $13.3^{\circ}$ when maximally. So we determined $73^{\circ}$ as appropriate slope angle of part in contact with face of the DTIS and by considering that the standard variation was great, we designed control gears to adjust the slope of the camera view axis and to regulate the object distance. Conclusions: We designed a optimized mechanical structure in object distance and slope angle of part in contact with face of the DTIS.

• 한국정보통신학회논문지
• /
• 제15권2호
• /
• pp.455-461
• /
• 2011

블록정합 기법을 이용한 객체추적에서 크기가 다양하고 수시로 변하는 객체를 추적하기 위해 고정 정합블록을 사용하는 것은 적합하지 못하다. 본 논문은 동적 환경을 위한 적응적 정합블록을 정의하고, 이를 위한 블록정합 알 고리즘을 제안한다. 정합블록은 $42{\times}42$ 화소의 넓은 영역에 $10{\times}10$ 화소의 주 블록과 $6{\times}6$ 화소의 부 블록 8개로 구성되고, 영역 중심에 위치한 주 블록은 객체 블록으로 사용되고, 영역의 외곽에 위치한 부 블록은 객체블록을 위한 후보 블록으로 사용된다. 제안된 알고리즘은 부 블록에서 이전 10 프레임의 움직임 벡터를 이용해 객체블록을 추출하고, 주 블록과 추출된 객체블록을 이용해 블록정합을 수행한다. 성능 평가를 위한 실험들은 제안된 알고리즘이 정합블록에서 유효한 객체블록만을 적절히 추출하고, 자유로운 움직임을 갖는 객체를 영상의 중심 영역에 유지시켜 주는 것을 보여주고 있다.

• 방재기술
• /
• 통권15호
• /
• pp.28-38
• /
• 1993

This report is explain the nature of smoke and the principle of smoke detection. The object of this research is to understand the hazard of smoke and select the optimum smoke detectors, according to the types of smoke and the particle size of smoke produced by fire

• 한국자기학회:학술대회 개요집
• /
• 한국자기학회 2008년도 Asian Magnetics Conference
• /
• pp.37.2-37.2
• /
• 2008

• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.876-887
• /
• 2018

In this paper, we propose an robust CAMShift method to track stage objects with a camera. In order to solve the problem of tracking object misdetection in existing CAMShift technique, MBR region is detected to separate the background and the subject, and the subject size of the region of interest is calculated to solve the problem of erroneously detecting a large region having a similar color distribution ratio. Also, by applying the color corelogram and MB-LBP to the part that can not be solved by the color ratio and the size limitation, accurate texture tracking is enabled by reflecting the texture characteristics. Experimental results show that the proposed method has good tracking performance for objects that do not deviate from the size of the subject set in the area of interest and accurately extracts the texture characteristics of different subjects with similar color distribution ratios.

• 한국컴퓨터정보학회논문지
• /
• 제22권12호
• /
• pp.79-85
• /
• 2017

In this paper, we propose a CNN-based swimmer detection algorithm. Every year, water safety accidents have been occurred frequently, and accordingly, intelligent video surveillance systems are being developed to prevent accidents. Intelligent video surveillance system is a real-time system that detects objects which users want to do. It classifies or detects objects in real-time using algorithms such as GMM (Gaussian Mixture Model), HOG (Histogram of Oriented Gradients), and SVM (Support Vector Machine). However, HOG has a problem that it cannot accurately detect the swimmer in a complex and dynamic environment such as a beach. In other words, there are many false positives that detect swimmers as waves and false negatives that detect waves as swimmers. To solve this problem, in this paper, we propose a swimmer detection algorithm using CNN (Convolutional Neural Network), specialized for small object sizes, in order to detect dynamic objects and swimmers more accurately and efficiently in complex environment. The proposed CNN sets the size of the input image and the size of the filter used in the convolution operation according to the size of objects. In addition, the aspect ratio of the input is adjusted according to the ratio of detected objects. As a result, experimental results show that the proposed CNN-based swimmer detection method performs better than conventional techniques.

• 한국분무공학회지
• /
• 제14권2호
• /
• pp.77-83
• /
• 2009

In this study, the effect of important parameters such as the pixel size and number of a CCD, the object distance, the wavelength of laser, and the particle diameter on the depth of focus in digital in-line particle holography were investigated. The depth of focus in several different cases was calculated using simulation holograms and detailed description of the depth of focus in digital particle holography was presented. The depth of focus is directly proportional to the object distance and the particle size. With the increase of the wavelength of laser, the depth of focus is decreased. The depth of focus is also inversely proportional to the pixel size and number of a CCD. Using the data of depth of focus from simulation holograms and a data-fitting software, we obtained the prediction equations of depth of focus for typical CCD cameras. Finally, the prediction equations of depth of focus in digital particle holography were verified by investigating real holograms of the calibration target in different cases and satisfied agreement between measured values and predicted values was confirmed.