• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.5
• /
• pp.3-10
• /
• 2019

This study is purposed to analyze of House Vision exhibition and projects in Japan. The contemporary residence has been planned and designed with fixed territory and boundary of rooms. According to the symposium of House Vision, the spatial boundary can be studied in the aspect of territory that molds the experience of residents. So, this study reviews Aldo van Eyck's concept of 'in-between'. Through the analysis, House Vision exhibition is revealed that the housing models present architectural characteristics of middleware and third place. The cognition of internal and external boundary stems from movements and activities of residents. That is the dwelling and residential space determined by users and residents. In this regard, 'in-between' of House Vision has structures(multilayer) causing various relationships to be perceived, so as to connect with the dwelling and activities of residents. As a result, it has relational meanings of sharing, as well as makes possible other community life to be done. According to the projects of House Vision, the units and cores have created the new connections and relationships between privacy and publicity. In conclusion, this research shows a new direction of the spatial strategies on House Vision exhibition in Japan.

• 한국방재학회:학술대회논문집
• /
• 2011.02a
• /
• pp.39-39
• /
• 2011

This study presents an effective vision-based system for cable bridge damage detection. In theory, cable bridges need to be inspected the outer as well as the inner part. Starting from August 2010, a new research project supported by Korea Ministry of Land, Transportation Maritime Affairs(MLTM) was initiated focusing on the damage detection of cable system. In this study, only the surface damage detection algorithm based on a vision-based system will be focused on, an overview of the vision-based cable damage detection is given in Fig. 1. Basically, the algorithm combines the image enhancement technique with principal component analysis(PCA) to detect damage on cable surfaces. In more detail, the input image from a camera is processed with image enhancement technique to improve image quality, and then it is projected into PCA sub-space. Finally, the Mahalanobis square distance is used for pattern recognition. The algorithm was verified through laboratory tests on three types of cable surface. The algorithm gave very good results, and the next step of this study is to implement the algorithm for real cable bridges.

• Transactions of Materials Processing
• /
• v.5 no.4
• /
• pp.343-352
• /
• 1996

One of the preferred methods that can be used to verify the results of finite element analysis is to measure surface strains of the deformed part for purpose of direct comparison with simulation results. Instead of using the usual manual method the vision-based measurement method is capable of determining surface geometry and strain from the deformed grid pattern automatically with the help of a computer. To obtain strain distribution over an area, the coordinates of such a surface grid are determined from the multiple video images by applying the photogrammetry principle. Methods to improve the overall accuracy of the vision-based strain measurement system are explored and the possible accuracies that can be attained by such a measurement method are discussed. A major emphasis is placed on the initial grid application method its accuracy and ease of subsequent image processing. Finite element analyses of limiting dome height(LDH) test are carried out and the results of them are compared with exsperimen-tal data.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2003.11a
• /
• pp.3-10
• /
• 2003

Developments in science and technology based on computer technology influenced military fields and created up-to-date weapons and equipment, and as a result, which is changing the war accomplishing methods of the future warfare. Due to these changes in the war accomplishing methods, the army command centers are requested to make changes in their decision-making process. In other words, they need to apply more scientific methods rather than just build a scheme by the mere analysis of commanders and the staffs as in the past. Consequently, we propose a model, Vision 21 we developed as a war game model for division-size unit analysis use, in the COA development process, which is the most important part in establishing the OPLAN for mission accomplishment. Vision 21, with a comparative analysis of the other COA built in the COA development process, can be applied to making the best COA. Model employment concept can let us choose the best COA, operating war games on condition that the COA of the opposite forces is fixed and ours sequentially opposed against, and with a comparative analysis also. Moreover, if the time available is limited, before establishing several courses, we can apply the COA to the process for making the best decision, analysing in stages or by main phases and not establishing several courses for a special purpose.

• Proceedings of the Optical Society of Korea Conference
• /
• 2006.02a
• /
• pp.185-186
• /
• 2006

• 한국노년학
• /
• v.37 no.1
• /
• pp.1-14
• /
• 2017

The purpose of this study was to examine the effect of vision and hearing limitation on the onset of disability among Korean elderly with the consideration of social participation and depression. Study population consisted of 2,670 people aged 65 and above who participated in both the 1st(2006) and 2nd(2008) wave of the Korean Longitudinal Study of Aging(KLoSA), and also reported no ADL or IADL disability in 2006. As the results, first, it found that vision and hearing limitation, social participation, and depression were significant risk factors for the onset of IADL disability in unadjusted analysis. After multivariable adjustment, however, only vision limitation showed significant association with the onset of IADL disability. Second, in the logistic analysis with four categorized variables(vision/hearing limitation + social participation, vision/hearing limitation + depression), the elderly who had vision or hearing limitation had a significantly 1.7 times higher odds ratio for disability onset if they also had low social participation compared with those who had no vision or hearing limitation, and high social participation. Whereas, depression was not significantly associated with the relationship between vision or hearing limitation, and disability onset. The study suggests that the intervention program developed to prevent social isolation of older people with vision or hearing limitation, may be helpful to reduce and postpone the risk of disability onset as well as early detection and treatment of vision or hearing problems.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.1
• /
• pp.41-50
• /
• 2020

The National Geographic Information Institute of Korea takes digital aerial photograph images every two years to make and modify/renew the digital map. The cameras for aerial photogrammetry to capture these digital aerial photographs are divided into frame types and line types. Computer vision analysis of aerial photograph images was only possible for frame type. Thus, in this study, Line type aerial photograph images was intended to generate geospatial information through computer vision analysis, and forest geospatial information was created as a method for the utilization of aerial picture images. As a result, geospatial information generated by computer vision analysis of line type aerial photograph images showed that RMSE of horizontal and vertical position errors was less than quadruple that of GSD. Forest geospatial information was generated using geospatial information generated by computer vision analysis. It was confirmed that extraction of the crown of tree and calculation of tree height are possible. Through this study, it is expected that utilization of aerial photograph images will be improved.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.101-108
• /
• 2019

Due to recent improvements in computer processing speed and image processing technology, researches are being actively carried out to combine information from camera with existing GNSS (Global Navigation Satellite System) and dead reckoning. In this study, developed a vision-based positioning assistant algorithm to estimate the distance to the object from stereo images. In addition, GNSS/on-board vehicle sensor/vision based positioning algorithm is developed by combining vision based positioning algorithm with existing positioning algorithm. For the performance analysis, the velocity calculated from the actual driving test was used for the navigation solution correction, simulation tests were performed to analyse the effects of velocity precision. As a result of analysis, it is confirmed that about 4% of position accuracy is improved when vision information is added compared to existing GNSS/on-board based positioning algorithm.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.2
• /
• pp.457-462
• /
• 2018

Railway system has been unmanned and high-speedy. Korean railway corporations need a more effective and smarter system for operation and maintenance. So there are many theses that studied the intelligent operation and maintenance system using vision based technologies for railway corporation. This paper analyzes domestic theses which studied the intelligent vision based system for railway safety, railway vehicle and facilities and proposes research which uses the more powerful vision based technology with deep-learning for railway corporation.