• 한국정보통신학회논문지
• /
• 제22권4호
• /
• pp.617-623
• /
• 2018

본 논문에서는 형태 정합 및 포아송 방정식을 기반으로 객체와 배경과의 이음매가 없는 효율적인 동영상 합성 기법을 제안한다. 동영상 합성 기법은 영상 분할 과정과 영상 조합 과정으로 구성된다. 영상 분할 과정에서는 먼저 첫번째 프레임에 대해 사용자가 3 영역 지도를 설정한 후, 그랩 컷(grab cut) 알고리즘을 수행한다. 그리고 객체와 배경의 색상, 밝기, 텍스쳐 등이 유사할 경우 영상 분할의 성능이 감소될 수 있음을 감안하여, 현재 프레임과 이전 프레임 객체들 간의 형태 정합을 통해 현재 프레임에서 영상 분할된 객체를 보정한다. 영상 조합 과정에서는 포아송 방정식을 이용하여 객체와 목표 동영상의 배경이 서로 이음매 없이 조합되도록 하며, 또한 사용자가 설정한 움직임 경로에 따라 객체를 배치한다. 모의실험을 통해 제안된 방법이 합성된 동영상의 자연성 뿐만 아니라 수행 시간 면에서 우수함을 알 수 있었다.

• 한국의류학회지
• /
• 제6권2호
• /
• pp.49-55
• /
• 1982

The purpose of this study was to analyze the factorial structure of the criteria on clothing selection. Data were obtained from 219 housewives in Seoul. 95 likert type questions were selected from the existing questionnaires and from the open end questions. The items were analyzed for discriminating power, followed by the factor analysis. 57 items were subjected to the principal component analysis with orthogonal rotation after extraction of 5 major factors. 47 items were found to be significantly loaded to at least one of the five factors. The factors had the following characteristics: Factor I. The persons scoring high on this factor would invest time and energy in their clothes to achieve their image and individuality. They were interested in clothes, appearance and fashion. Factor II. The persons scoring high on this factor were more concerned about the practicality of clothing, such as ease-of-care, comfort, texture and quality of fabric. They would not select the clothes which soiled easily and would not perform as expected. Factor III. High scores on this factor were associated with the eagerness to get the cloth-ing value for the money. They would make a long plan to buy an expensive clothing and choose a unique clothing regardless of fashion. Factor IV. A high score on this factor was suggestive of modesty. They were willing to buy inconspicuous clothes, such as dark or muted colors, small prints and conservative styles. Factor V. High scores on this factor were characterized by the desire for conformity and approval of their friends. This result may be used to develop an instrument to measure the criteria on clothing selection of consumer.

• 자원환경지질
• /
• 제34권2호
• /
• pp.205-215
• /
• 2001

본 연구는 1998년 경기도 장흥지역에서 발생한 산사태의 취약성 분석을 목표로 산사태와 공간정보사이의 연관성을 정량적으로 밝히는데 목적이 있다. 산사태 발생위치는 원격탐사 영상과 야외 조사를 통해 작성하였으며, GIS 기반의 공간 데이터베이스로 지형, 토양, 임상 및 토지이용자료를 구축하였다. 지형자료로는 경사, 방위, 곡률을, 토양자료로는 토질, 토양 배수, 토양 모재, 유효 토심을, 임상자료로는 임상, 영급, 경급 및 밀도를 이용하였다. 산사태 발생과 공간정보사이의 관계는 우도비를 이용하여 정량적으로 추출하였으며, 경기도 용인지역에서 발생한 산사태의 분석결과와 비교를 하였다. 그리고 계산된 우도비를 이용하여 연구지역 전체에 대한 산사태 취약성 지수도를 작성하였다. 연구결과, 산사태 발생과 밀접한 관련이 있는 공간정보를 추출할 수 있었으며, 이러한 분석결과는 산사태 피해 예방을 위한 방재사업, 국토개발 계획 등의 기초자료로 이용될 수 있을 것이다.

• 대한공간정보학회지
• /
• 제10권1호
• /
• pp.19-26
• /
• 2002

인터넷에 3차원 GSIS 데이터를 제공하기 위해서는 VRML로 3차원 지형을 생성하는 방법과 지형공간정보 데이터의 자동연결 방법에 관한 연구가 필요하다. VRML은 3차원 물체들의 상호관계를 표현하는데 표준적인 언어로서 온라인상에 연결된 가상의 세계를 시뮬레이션할 때 쓰인다. 이는 가상세계를 표현할 뿐만 아니라 파일로 저장하여 웹 이용자들 중의 한사람에게 가상세계를 보여줄 수도 있다. 본 연구에서는 수치지도 데이터, 항공사진, VRML 스크립터로 구성된 VRML모델을 이용하는 인터넷상에서 3차원 GSIS를 제공하는 방법을 보여주고자 한다. 인터넷상에서 3차원 GSIS 제공하는 것과 항공사진들을 이용해서 정밀하게 지도를 제작하는 방법을 알아보며 VRML로 수치지도와 항공사진으로 3차원 영상을 만들기 위해 어떠한 데이터가 가장 효율적인지 비교하였으며 3차원 지형데이터의 인터넷제공 방법에 대해 연구하였다.

• 한국산학기술학회논문지
• /
• 제14권3호
• /
• pp.1459-1466
• /
• 2013

최근 들어, 주변의 환경 분석을 보다 효과적으로 수행하기 위해서 많은 종류의 3차원 입체 카메라가 보급되고 있다. 본 논문에서는 주위 환경의 복잡도에 따라서 하이브리드 카메라의 수동형과 능동형 카메라를 적응적으로 스위칭함으로써 3차원의 영상정보를 보다 정확하게 추출할 수 있는 메커니즘을 제안한다. 제안된 방법에서는 먼저 초기영상을 받아들이고, 이 입력영상으로부터 주변의 환경을 대표할 수 있는 주요 특징인 밝기 특징과 텍스처 특징을 추출한다. 그런 다음, 추출된 밝기와 텍스처 특징값을 가장 잘 수용할 수 있는 카메라를 선택하는 규칙을 생성함으로써 하이브리드 카메라를 적응적으로 스위칭한다. 실험에서는 수동형과 능동형으로 구성된 하이브리드 입체 카메라를 구성하고, 제안된 적응적인 스위칭 알고리즘을 하이브리드 카메라에 적용하여 성능을 측정하기 위한 실험결과를 기술하며, 제안된 방법이 신뢰성 있게 동작함을 보여준다.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.288-296
• /
• 2021

Automated face recognition in a runtime environment is gaining more and more important in the fields of surveillance and urban security. This is a difficult task keeping in mind the constantly volatile image landscape with varying features and attributes. For a system to be beneficial in industrial settings, it is pertinent that its efficiency isn't compromised when running on roads, intersections, and busy streets. However, recognition in such uncontrolled circumstances is a major problem in real-life applications. In this paper, the main problem of face recognition in which full face is not visible (Occlusion). This is a common occurrence as any person can change his features by wearing a scarf, sunglass or by merely growing a mustache or beard. Such types of discrepancies in facial appearance are frequently stumbled upon in an uncontrolled circumstance and possibly will be a reason to the security systems which are based upon face recognition. These types of variations are very common in a real-life environment. It has been analyzed that it has been studied less in literature but now researchers have a major focus on this type of variation. Existing state-of-the-art techniques suffer from several limitations. Most significant amongst them are low level of usability and poor response time in case of any calamity. In this paper, an improved face recognition system is developed to solve the problem of occlusion known as FRS-OCC. To build the FRS-OCC system, the color and texture features are used and then an incremental learning algorithm (Learn++) to select more informative features. Afterward, the trained stack-based autoencoder (SAE) deep learning algorithm is used to recognize a human face. Overall, the FRS-OCC system is used to introduce such algorithms which enhance the response time to guarantee a benchmark quality of service in any situation. To test and evaluate the performance of the proposed FRS-OCC system, the AR face dataset is utilized. On average, the FRS-OCC system is outperformed and achieved SE of 98.82%, SP of 98.49%, AC of 98.76% and AUC of 0.9995 compared to other state-of-the-art methods. The obtained results indicate that the FRS-OCC system can be used in any surveillance application.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1445-1456
• /
• 2018

Environment perception and three-dimensional (3D) reconstruction tasks are used to provide unmanned ground vehicle (UGV) with driving awareness interfaces. The speed of obstacle segmentation and surrounding terrain reconstruction crucially influences decision making in UGVs. To increase the processing speed of environment information analysis, we develop a CPU-GPU hybrid system of automatic environment perception and 3D terrain reconstruction based on the integration of multiple sensors. The system consists of three functional modules, namely, multi-sensor data collection and pre-processing, environment perception, and 3D reconstruction. To integrate individual datasets collected from different sensors, the pre-processing function registers the sensed LiDAR (light detection and ranging) point clouds, video sequences, and motion information into a global terrain model after filtering redundant and noise data according to the redundancy removal principle. In the environment perception module, the registered discrete points are clustered into ground surface and individual objects by using a ground segmentation method and a connected component labeling algorithm. The estimated ground surface and non-ground objects indicate the terrain to be traversed and obstacles in the environment, thus creating driving awareness. The 3D reconstruction module calibrates the projection matrix between the mounted LiDAR and cameras to map the local point clouds onto the captured video images. Texture meshes and color particle models are used to reconstruct the ground surface and objects of the 3D terrain model, respectively. To accelerate the proposed system, we apply the GPU parallel computation method to implement the applied computer graphics and image processing algorithms in parallel.

• 복식문화연구
• /
• 제27권3호
• /
• pp.222-238
• /
• 2019

This study is aimed at applying the philosophical concept of "$diff{\acute{e}}rance$" to contemporary men's fashion design, which could effectively show the shift in thinking. For the study method, the author examined the theoretical background of deconstruction and prepared the standard of analysis by organizing the concept of "$diff{\acute{e}}rance$," which exists at the center of philosophy. This study selected the three most popular brands: Maison Margiela, Comme des Garcons, and Yohji Yamamoto. The results are as follows. First, there is expression of perpetual reservation emphasizing time. This includes texture, patchworks, hems with ladder, and exposure of seam that expresses the trace of time flow and delayed delivery of immediate meaning, and the expression creates delay between major and minor and leads to consistent role exchange. Second, the trace of blank that emphasizes the space gives a visual sense of weight on spares with the intentionally granted space, as well as the space that is the trace of trace and creates a sense of depth through the direction of empty space. Third, the space created in the process of wearing cloth is visualized, the structure of clothing is deconstructed, and the movement from the process recomposes the shape of space and expands the definition that enables expansion of time and space. Fourth, the undetermined relationship expresses the border of time and space visually and deconstructs time and space. The approaches are mostly constructive, demonstrating an avant-garde form of clothes-wearing to show the non-form or imbalance condition.

• 한국정보기술학회논문지
• /
• 제17권9호
• /
• pp.99-112
• /
• 2019

도로 포장면의 크랙(crack)은 도로포장 구조의 열화를 입증하는 중요한 신호와 증상이다. 카메라 영상기반 도로포장 크랙 탐지는 강도 비균질성, 위상 복잡성, 낮은 대조도 및 노이즈성의 텍스처 배경 때문에 어려운 문제이다. 본 논문은 흑백영상에 대하여 깊은 신경망(DNN)에 기반하여 픽셀수준의 도로 크랙 탐지 및 분할 문제에 대해 다룬다. 변형된 U-net 네트워크와 고수준 특징 네트워크를 포함하는 새로운 DNN 구조를 제안한다. 본 연구의 중요 기여는 융합 층을 통해 공급되는 이들 네트워크의 결합 방법이다. 우리가 아는 한, 본 연구는 보도블럭 크랙 분할 및 탐지 문제를 결합을 소개한 최초의 논문이다. 크랙 탐지 및 분할의 시스템 성능은 새로운 구조를 사용하여 급격히 향상되었다. 제안된 시스템을 2개의 공개 데이터셋­크랙 포레스트 데이터셋(CFD)와 AigleRN 데이터셋­에 대하여 구현하고 평가하였다. 본 논문의 시스템은 여덟 가지의 최신 알고리즘과 같은 데이터셋으로 실험을 하였을 때, 가장 뛰어난 결과를 보여주었다.

• 보존과학회지
• /
• 제38권4호
• /
• pp.301-313
• /
• 2022

We made a Korean white porcelain or Joseon Baekja jar and based on the raw materials used and reproductions of each stage, we aimed to compare and analyze the physicochemical changes of the raw materials such as clay at each manufacturing stage, as well as identify the characteristics and correlations. Although the basic main components of clay and glaze material are similar, their texture becomes denser in the process of bisque firing pottery (Chobeol-pyeon) and glaze firing pottery (Jaebeol-pyeon), and we confirmed that in addition to the tendency of increasing vitrification, low-temperature minerals such as mica and illite gradually disappeared, while high-temperature minerals such as cristobalite were newly created. This phenomenon has also been verified by the rapid decrease in absorption rate while the change in specific gravity was small. In addition, the color was greatly affected by the firing atmosphere, and the yellow-red chromaticity of the raw materials was higher during bisque firing but showed a rapidly decreasing characteristic during glaze firing. The value of magnetic susceptibility, which is related to iron (Fe) component, showed a tendency to decrease in glaze firing pottery. CT images were confirmed as a method that can indirectly estimate the change in the material properties of the object step-by-step for the entire object. In conclusion, the study of manufacturing stages of reproduction can provide basic data for scientific research on the estimation of porcelain and pottery making technology and changes in raw materials.