• 한국터널지하공간학회 논문집
• /
• 제24권6호
• /
• pp.513-524
• /
• 2022

터널을 비롯한 여러 가지 기반시설물에 발생한 콘크리트 균열을 영상과 딥러닝 기반으로 자동 탐지하는 연구가 최근 활발히 이루어지고 있다. 이러한 연구성과를 실제 현장에 적용하려면 딥러닝 모델의 신뢰성을 설명할 수 있어야한다. 본 연구에서는 선형성이 강한 균열의 기하적인 특성을 고려했을 때 화소 기반으로 계산하는 기존 평가지표가 충분치 않다는 점을 지적하며, 균열 분할 딥러닝 모델의 성능을 더 합리적으로 설명할 수 있는 다른 평가지표를 제시하고 비교 분석한다. 먼저 선형 객체의 유사성을 측정할 수 평가방법을 제시한다. 구체적으로는 기준 데이터에 허용 버퍼(tolerance buffer)를 부여하여 평가하는 방법을 설계, 구현, 검증한다. 실험 결과 본 연구에서 제안하는 방법은 균열 분할 딥러닝 모델 평가시 기존 대비 과대평가 또는 과소평가 문제를 해결할 수 있었으며, 화소 기반 성능 평가 지표에 비해 균열 분할 딥러닝 모델의 성능을 더 잘 설명할 것으로 기대한다.

• Journal of Electrical Engineering and Technology
• /
• 제10권1호
• /
• pp.372-378
• /
• 2015

Background subtraction is the first processing stage in video surveillance. It is a general term for a process which aims to separate foreground objects from a background. The goal is to construct and maintain a statistical representation of the scene that the camera sees. The output of background subtraction will be an input to a higher-level process. Background subtraction under dynamic environment in the video sequences is one such complex task. It is an important research topic in image analysis and computer vision domains. This work deals background modeling based on modified adaptive Gaussian mixture model (GMM) with three temporal differencing (TTD) method in dynamic environment. The results of background subtraction on several sequences in various testing environments show that the proposed method is efficient and robust for the dynamic environment and achieves good accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.430-433
• /
• 1996

The shape of an object plays a very important role in pattern analysis and classification. Roughly, the researches on this topic can be classified into three fields, i.e. (i) edge detection, (ii) dominant points extraction, and (iii) shape recognition and classification. Many works have been done in these three fields. However, it is very seldom to see the research that discusses the connection relationship of objects. This problem is very important in robot assembly systems. Therefore, here we focus on this problem and discuss how to recover the connection relationship of planar objects. Our method is based on the partial curve identification algorithm. The experiment results show the efficiency and validity of this method.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2005년도 춘계학술발표대회
• /
• pp.737-740
• /
• 2005

복수의 화제가 혼합되어 있는 문서에서 각 화제의 경계부분을 구분하여 결정하는 단락분할 시스템을 개발한다. 이 기술은 정보검색의 분야에만 한정되지 않고 다양한 분야 예를 들면, 문서분류 및 요약 등의 기초연구에서 중요한 역할을 담당할 기술이다. 본 논문에서는 화제의 출현, 계속, 전환 시점을 고려하여 출현하는 각 화제의 단락구분 방법에 대하여 제안한다. 단락 구분 시 문서의 의미적인 실마리가 끊어지지 않도록 단락을 추출하는 방법을 제안한다.

• 제어로봇시스템학회논문지
• /
• 제17권5호
• /
• pp.479-483
• /
• 2011

The automation of production process is actively expanding for the purpose of the cost reduction and quality assurance. Among these, automatic tracking of the product along the whole process of the production is also important topic. Typically this is done by adopting OCR technology. Conventional OCR technology operates well on the rather good quality of the image like as printed characters on the paper. In industrial application, IDs are marked on the metal surface, and this cause the height difference between background material and character. Illumination systems that guarantee an image with good quality may be a solution, but it is rather difficult to design such an illumination system. This paper proposes an algorithm for the recognition of vehicle's ID characters using edge projection and PCA (Principal Component Analysis). Proposed algorithm robustly operates under illumination change using the same parameters. Experimental results show the feasibility of the proposed algorithm.

• 정보관리학회지
• /
• 제39권3호
• /
• pp.99-132
• /
• 2022

본 연구의 목적은 LDA 토픽모델링 결과와 BERTopic 토픽모델링 결과를 합성하는 방법론인 Augmented and Extended Topics(AET)를 제안하고, 이를 사용해 문헌정보학 분야의 연구주제를 분석하는 데 있다. AET의 실제 적용결과를 확인하기 위해 2001년 1월부터 2021년 10월까지의 Web of Science 내 문헌정보학 학술지 85종에 게재된 학술논문 서지 데이터 55,442건을 분석하였다. AET는 서로 다른 토픽모델링 결과의 관계를 WORD2VEC 기반 코사인 유사도 매트릭스로 구축하고, 매트릭스 내 의미적 관계가 유효한 범위 내에서 매트릭스 재정렬 및 분할 과정을 반복해 증강토픽(Augmented Topics, 이하 AT)을 추출한 뒤, 나머지 영역에서 코사인 유사도 평균값 순위와 BERTopic 토픽 규모 순위에 대한 조화평균을 통해 확장토픽(Extended Topics, 이하 ET)을 결정한다. 최적 표준으로 도출된 LDA 토픽모델링 결과와 AET 결과를 비교한 결과, AT는 LDA 토픽모델링 토픽을 한층 더 구체화하고 세분화하였으며 ET는 유효한 토픽을 발견하였다. AT(Augmented Topics)의 성능은 LDA 이상이었으며 ET(Extended Topics)는 일부 경우를 제외하고 대부분 LDA와 유사한 수준의 성능을 나타내었다.

• 복식
• /
• 제62권7호
• /
• pp.79-96
• /
• 2012

Creativity is a rising topic in the current society. The emphasis on creativity is valued as a key factor for success in all areas including but not limited to politics, economy, culture, arts and design. The field of Fashion design is probably one of the few areas that talk about creativity as a necessary quality to survive. The purpose of this study is to introduce TRIZ(Teoriya Reshniya Izobretatelsskikh Sadatch) as a theoretical tool to generate creativity in fashion design. TRIZ is a creative method of problem solving based on data analysis of outcomes invented by engineering. The fundamental concept of TRIZ has been researched through documentary studies, and practical case studies of product designs are used. Fashion design cases from Comme des Garcons by Rei Kawakubo are used to apply TRIZ in fashion design. Rei Kawakubo's design philosophy has been studied through fashion writings and visual sources in books, exhibition catalog, www. style. com and online shopping mall sites. This study has selected four principles among forty inventive theories of TRIZ: segmentation; asymmetry; consolidation; and preliminary action to apply to Rei Kawakubo's fashion design. As a result, TRIZ can be applicable to fashion design as a creative thinking methodology. By using the four principles of TRIZ, this study shows how Rei Kawakubo's design enhanced its efficiency and aesthetics of the products and was distinguished from existing items. It is meaningful to demonstrate a possibility of adopting engineering based creative methodology in fashion design to widen the perspective and to raise a question for the need of interdisciplinary creative methodology with traditional aesthetic approach in fashion design.

• 방송공학회논문지
• /
• 제27권5호
• /
• pp.619-628
• /
• 2022

얼굴 인식 및 얼굴 생성이 다양한 분야에서 큰 주목을 받고 있지만, 얼굴 이미지를 모델 학습에 사용하는데 따른 개인 정보 문제는 최근 큰 문제가 되고 있다. 본 논문에서는 소수의 실제 얼굴 이미지와 안면 마스크 정보로부터 다양한 속성을 가진 얼굴 이미지를 생성함으로써 개인 정보 침해 이슈를 줄일 수 있는 얼굴 편집 네트워크를 제안한다. 다수의 실제 얼굴 영상을 이용하여 얼굴 속성을 학습하는 기존의 방법과 달리 제안하는 방법은 얼굴 분할 마스크와 얼굴 부분 텍스처 영상을 스타일 정보로 사용하여 새로운 얼굴 이미지를 생성한다. 이후 해당 이미지는 각 참조 이미지의 스타일과 위치를 학습하기 위한 훈련에 사용된다. 제안하는 네트워크가 학습되면 소수의 실제 얼굴 영상과 얼굴 분할 정보만을 사용하여 다양한 얼굴 이미지를 생성할 수 있다. 실험에서 제안 기법이 실제 얼굴 이미지를 매우 적게 사용함에도 불구하고 새로운 얼굴을 생성할 뿐만 아니라 얼굴 속성 편집을 지역화하여 수행할 수 있음을 보인다.

• Computers and Concrete
• /
• 제33권4호
• /
• pp.425-443
• /
• 2024

Floods are among the most common natural hazards in urban areas. To mitigate the problems caused by flooding, unstructured data such as images and videos collected from closed circuit televisions (CCTVs) or unmanned aerial vehicles (UAVs) have been examined for flood management (FM). Many computer vision (CV) techniques have been widely adopted to analyze imagery data. Although some papers have reviewed recent CV approaches that utilize UAV images or remote sensing data, less effort has been devoted to studies that have focused on CCTV data. In addition, few studies have distinguished between the main research objectives of CV techniques (e.g., flood depth and flooded area) for a comprehensive understanding of the current status and trends of CV applications for each FM research topic. Thus, this paper provides a comprehensive review of the literature that proposes CV techniques for aspects of FM using ground camera (e.g., CCTV) data. Research topics are classified into four categories: flood depth, flood detection, flooded area, and surface water velocity. These application areas are subdivided into three types: urban, river and stream, and experimental. The adopted CV techniques are summarized for each research topic and application area. The primary goal of this review is to provide guidance for researchers who plan to design a CV model for specific purposes such as flood-depth estimation. Researchers should be able to draw on this review to construct an appropriate CV model for any FM purpose.

• 유통과학연구
• /
• 제14권12호
• /
• pp.23-30
• /
• 2016

Purpose - As socially responsible consumption increases, green marketing emerges as a new philosophy in marketing. A number of companies are now putting forth green marketing strategies. But there is no single definition of "green brand" that can be used interchangeably. In this paper, we attempt to explore the meaning for "green brand," especially in Information and Technology products. Research design, data, and methodology - The author developed qualitative and quantitative research design. In particular, the paper approaches this topic from the Asian consumers' perspective and applies ethical concepts to green brand research. For this, Chinese and Korean consumers were used as consumer segmentation variables to investigate their ethical perspectives. Results - Qualitative research showed that there are several attributes and benefits we need to consider for green brand. Quantitative study showed positive correlations of the two variables: the higher the consumer ethics are, the more they prefer green brands. Conclusions - The current study shows that consumers clearly have a certain propensity toward green brand equity. Thus, marketers should consider the consumers' evaluation about green brands. This paper also proposes that ethics have a close relationship with green brand equity, and companies may use ethics in marketing strategy management.