• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.361-370
• /
• 2020

Automatic building material recognition has been a popular research interest over the past decade because it is useful for construction management and facility management. Currently, the extensively used methods for automatic material recognition are mainly based on 2D images. A terrestrial laser scanner (TLS) with a built-in camera can generate a set of coloured laser scan data that contains not only the visual features of building materials but also other attributes such as material reflectance and surface roughness. With more characteristics provided, laser scan data have the potential to improve the accuracy of building material recognition. Therefore, this research aims to develop a TLS-based building material recognition method by combining machine learning techniques. The developed method uses material reflectance, HSV colour values, and surface roughness as the features for material recognition. A database containing the laser scan data of common building materials was created and used for model training and validation with machine learning techniques. Different machine learning algorithms were compared, and the best algorithm showed an average recognition accuracy of 96.5%, which demonstrated the feasibility of the developed method.

• 한국정보통신학회논문지
• /
• 제24권3호
• /
• pp.341-348
• /
• 2020

인간의 눈과 같이 이미지에서 유용한 정보를 추출하는 기능은 인공지능 컴퓨터 구현에 필수적인 인터페이스 기술이다. 이미지에서 건물을 인식하여 추론하는 기술은 다양한 형태의 건물 외관, 계절에 따른 주변 잡음 이미지의 변화, 각도 및 거리에 따른 왜곡 등으로 다른 이미지 인식 기술 보다 인식률이 떨어진다. 지금까지 제시된 컴퓨터 비전(Computer Vision) 기반의 건물 인식 알고리즘들은 건물 특성을 수작업으로 정의하기 때문에 분별력과 확장성에 한계가 있다. 본 논문은 최근 이미지 인식에 유용한 딥러닝의 CNN(Convolutional Neural Network) 모델을 활용하는데 건물 외관에 나타나는 변화, 즉 계절, 조도, 각도 및 원근에 의해 떨어지는 인식률을 향상시키는 새로운 방법을 제안한다. 건물 전체 이미지와 함께 건물의 특징을 나타내는 부분 이미지들, 즉 창문이나 벽재 이미지의 데이터 세트를 함께 학습시키고 건물 인식에 활용함으로써 일반 CNN 모델 보다 건물 인식률을 약 14% 향상됨을 실험으로 증명하였다.

• 로봇학회논문지
• /
• 제8권2호
• /
• pp.82-91
• /
• 2013

This paper proposes a building recognition algorithm using watershed image segmentation algorithm and integrated region matching (IRM). To recognize a building, a preprocessing algorithm which is using Gaussian filter to remove noise and using canny edge extraction algorithm to extract edges is applied to input building image. First, images are segmented by watershed algorithm. Next, a region adjacency graph (RAG) based on the information of segmented regions is created. And then similar and small regions are merged. Second, a color distribution feature of each region is extracted. Finally, similar building images are obtained and ranked. The building recognition algorithm was evaluated by experiment. It is verified that the result from the proposed method is superior to color histogram matching based results.

• 한국지리정보학회지
• /
• 제11권3호
• /
• pp.136-150
• /
• 2008

항공사진이나 LiDAR 데이터를 이용하여 건물의 자동 추출에 있어서 많은 연구가 이루어졌지만, 3차원 위치정보와 영상의 형상정보라는 두 데이터의 장점을 융합하여 정확도를 향상시킬 수 있다. 이를 위하여 본 연구에서는 등고선 기반의 건물인식 알고리즘을 사용하여 LiDAR 데이터를 이용한 건물 인식 정확도를 향상시키고, 항공사진을 이용하여 건물 경계의 정교화도 추구하였다. 등고선기반 건물 인식 방법은 건물의 경계와 지붕구조물 정보를 생성할 수 있으며, 기존 TIN기반 인식 방법이나 NDSM기반 방법보다 우수한 건물 탐지 정확도를 보여주었다. 등고선으로 추정된 건물경계에 일정한 크기의 버퍼를 생성하여 항공사진의 경계영역을 한정시키고, double active contour를 사용하여 항공사진의 에지에 맞도록 건물경계를 정교화 하였다. 본 연구성과를 이용하여 향후 추출된 개체 경계의 일정 범위에서 최적의 정합을 수행하여 3차원 건물 경계를 생성할 수 있다.

• 대한토목학회논문집
• /
• 제26권3D호
• /
• pp.519-525
• /
• 2006

기존의 영역기반의 영상정합이나 에피폴라 기하 혹은 고도값 제한 등을 통해 정합의 탐색영역을 줄임으로 영상정합의 효율성을 높이는 방법들은 비슷한 형태의 고층 건물이 밀집되어 있는 대규모 도심지와 같은 경우 오정합의 가능성이 크며 정합에 소요되는 시간도 여전히 오래 걸리는 단점을 갖고 있다. 이러한 단점을 보완하기 위하여 건물 인식을 통한 영상정합법에 대하여 연구를 수행하고자 한다. 본 논문에서는 새로운 영상정합기법의 기초연구로서 컬러영상으로부터 경계정보와 색상 정보를 활용하여 동일 건물 인식에 관하여 실험을 수행하였다. 경계정보와 색상정보를 활용하기 위하여 각각 보완된 Hausdorff 거리개념과 보완된 컬러 인덱싱 기법을 적용하였다. 각각의 정보를 단독으로 활용한 경우 동일건물의 인식률이 경계정보의 경우 46.5%, 색상정보의 경우 7.1%로 매우 낮았으나, 두 가지 정보를 조합하여 인식을 실시한 결과 78.5%로 인식률이 높아지는 것을 확인할 수 있었다.

• 의료ㆍ복지 건축 : 한국의료복지건축학회 논문집
• /
• 제27권1호
• /
• pp.17-34
• /
• 2021

Purpose: The purpose of this study was to find out the difference in the priority level of recognition for universal design application in public spaces by gender. Method: ANOVA(analysis of variance) and post-hoc test were conducted to determine the priority level of recognition and pattern for the disabled, non-disabled, and experts classified into males and females. Results: There was no gender difference in the comparison by sector for all males and females. However, in comparing of domains and facilities, women showed a higher level of recognition than men in the building sector and cross domain. When comparing space consumers and producers by dividing them into male and female groups, women showed a higher level of recognition than men in producers, but there was no gender difference between consumers. In comparison by sector, domain and facility, women producers also showed a higher level of recognition in the road sector, park and recreation sector, sidewalk domain, four-spaces in the park and recreation sector, and six-spaces in the building sector than men producers. Also, in the building sector, women producers and consumers showed a higher recognition level than men. Comparing the disabled, non-disabled people and experts by dividing them into male and female groups, in the case of non-disabled people and experts, women showed a higher level of recognition than men, while men showed a higher level of recognition than women in the disabled. In addition, there were differences in recognition patterns in many spaces and facilities by gender. Implications: This study is meaningful in comparing the differences in the priority level of recognition and patterns between men and women to apply universal design for people of all ages and both sexes.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권2호
• /
• pp.1-7
• /
• 2020

The secure access the lighting, Heating, ventilation, and air conditioning (HVAC), fire safety, and security control boxes of building facilities is the primary objective of future smart buildings. This paper proposes an authorized user access to the electrical, lighting, fire safety, and security control boxes in the smart building, by using color grid coded optical camera communication (OCC) with face recognition Technologies. The existing CCTV subsystem can be used as the face recognition security subsystem for the proposed approach. At the same time a smart device attached camera can used as an OCC receiver of color grid code for user access authentication data sent by the control boxes to proceed authorization. This proposed approach allows increasing an authorization control reliability and highly secured authentication on accessing building facility infrastructure. The result of color grid code sequence received by the unauthorized person and his face identification allows getting good results in security and gaining effectiveness of accessing building facility infrastructure. The proposed concept uses the encoded user access authentication information through control box monitor and the smart device application which detect and decode the color grid coded informations combinations and then send user through the smart building network to building management system for authentication verification in combination with the facial features that gives a high protection level. The proposed concept is implemented on testbed model and experiment results verified for the secured user authentication in real-time.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 봄 학술논문 발표대회
• /
• pp.227-228
• /
• 2022

In order to achieve the goal of cost management, which is one of the three major management goals of building production, this paper introduces an approximate cost estimating automation technology in the design stage as the importance of predicting construction costs increases. BIM is used for accurate estimating, and the quantity of structural members and finishing materials is calculated by creating a 3D model of the actual building. However, only 2D basic design drawings are provided when making an estimating. Therefore, for accurate quantity calculation, digitization of 2D drawings is required. Therefore, this research calculates the quantity of concrete structural members by calculating the area for the recognition area through 2D drawing recognition technology incorporating computer vision. It is judged that the development technology of this research can be used as an important decision-making tool when predicting the construction cost in the design stage. In addition, it is expected that 3D modeling automation and 3D structural analysis will be possible through the digitization of 2D drawings.

• KIEAE Journal
• /
• 제13권6호
• /
• pp.23-28
• /
• 2013

Green Standard for Energy and Environmental Design(G-SEED) has been used for environmental friendly building certification since 2002. The certification criteria initialed with multi-residential building and now it expands to 10 criteria for new and existing building types. The purpose of this study is to understand current recognition of G-SEED from the survey of multi-complex residences in newtown. From the general question, 75.2% of responders answered the period of living term between 1~3 years, 58.6% lived in $102.48{\sim}132.23m^2$ residential area and 65.2% owned their residences. The 43.2% of respondents recognized that their residences gained G-SEED certification by G-SEED emblem(31.6%). This is the significant meaning to understand public recognition of G-SEED and how to approach the strategy for raising the G-SEED recognition. The responders expected positive influence for economical value from G-SEED and also 75.3% of responders agreed with that G-SEED would be a decision make to buy and rent their residences. Second, residents responded that the consideration issue for green building is energy & prevention of environmental pollution(27.7%) which carries equal concern in G-SEED criteria category. The result of this survey verifies that the current level recognition of G-SEED of the responder's perspectives still is not well-known but it confirmed they have a positive expectation. Therefore, from this result, G-SEED needs to draw road map with detail plans for developing G-SEED with public participation.

• 로봇학회논문지
• /
• 제1권2호
• /
• pp.172-179
• /
• 2006

In this paper, we present a practical place and object recognition method for guiding visitors in building environments. Recognizing places or objects in real world can be a difficult problem due to motion blur and camera noise. In this work, we present a modeling method based on the bidirectional interaction between places and objects for simultaneous reinforcement for the robust recognition. The unification of visual context including scene context, object context, and temporal context is also. The proposed system has been tested to guide visitors in a large scale building environment (10 topological places, 80 3D objects).