• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.3 no.2
• /
• pp.67-72
• /
• 2022

Ecological research relies on the interpretation of large amounts of visual data obtained from extensive wildlife surveys, but such large-scale image interpretation is costly and time-consuming. Using an artificial intelligence (AI) machine learning model, especially convolution neural networks (CNN), it is possible to streamline these manual tasks on image information and to protect wildlife and record and predict behavior. Ecological research using deep-learning-based object recognition technology includes various research purposes such as identifying, detecting, and identifying species of wild animals, and identification of the location of poachers in real-time. These advances in the application of AI technology can enable efficient management of endangered wildlife, animal detection in various environments, and real-time analysis of image information collected by unmanned aerial vehicles. Furthermore, the need for school education and social use on biodiversity and environmental issues using AI is raised. School education and citizen science related to ecological activities using AI technology can enhance environmental awareness, and strengthen more knowledge and problem-solving skills in science and research processes. Under these prospects, in this paper, we compare the results of our early 2013 study, which automatically identified African cichlid fish species using photographic data of them, with the results of reanalysis by CNN deep learning method. By using PyTorch and PyTorch Lightning frameworks, we achieve an accuracy of 82.54% and an F1-score of 0.77 with minimal programming and data preprocessing effort. This is a significant improvement over the previous our machine learning methods, which required heavy feature engineering costs and had 78% accuracy.

• Journal of Space Technology and Applications
• /
• v.1 no.1
• /
• pp.7-22
• /
• 2021

In this paper, we describe the results of the docking phase test in the ground environment of the rendezvous/docking technology verification satellite under development for the first time in Korea. rendezvous/docking technology is a high-level technology in space technology, which is also very important for accessing and performing tasks on relative objects in space orbit. In this paper, we describe the ground test results that the chaser finally docks the fixed target using an air bearing device. Based on the thrust control algorithm in the docking phase and the relative object recognition and relative distance estimation algorithm using visual-based sensors validated in this paper, we intend to use them for later expansion to rendezvous/docking algorithms in three-dimensional space for testing in space.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.477-482
• /
• 2021

The integrated underground space map system provides information on infrastructure that requires security, but to prevent rupture accidents during excavation work at the underground construction site, it must provide information on all underground facilities on the site. Providing additional information other than the object of interest to the user is a factor that increases the risk of information leakage of security data. In this paper, we design the visualization filtering method that when visualizing the integrated underground space map in the field, the visualization of entire underground facilities of interest to workers is performed, but visualization of other underground facilities is minimized to minimize the risk of security data information leakage. To this end, a visualization area of a certain distance for each of the underground facilities of interest was created, and an integrated visualization filter was created with spatial union operation. When the integrated underground map is output on the screen, only the objects located within the filter area are visualized using the generated filter information, and objects that exist outside are not visualized, thereby minimizing the provision of information to the user.

• Journal of Fashion Business
• /
• v.27 no.1
• /
• pp.61-76
• /
• 2023

The purpose of this study was to derive exotic products handled by Bon Marche department store, examine characteristics, and reveal the meaning of exotic taste in the 19th century. The research method is literature research centered on original materials of the time, such as old literature related to department stores, and films, newspapers, magazines, and periodicals as well as books and papers. Commercial catalogs and Agenda-Buvard published by Bon Marché were used as visual materials. Results are as follows. Exotic tastes of products of the Bon Marche department store in the late 19th century showed an oriental style centered on Persia, India, China, and Japan. Products from various regions such as Turkey, Spain, Algeria, Tunisia, England, Italy, and Russia were also accepted. These exotic tastes had the following contributions and meanings. First, they expanded items and product development and activated domestic industry through production of imitations and replicas. Second, before the advent of department stores, foreign items that came to Europe were exclusive properties of a few privileged classes. However, in the late 19th century, as the number of consumers who wanted to have a new status higher than themselves increased, exotic products of the Bon Marche department store became the object of desire for material pursuits toward the upper class rather than sentimental fantasies. Third, exotic tastes gradually spread to the public as production of products imitating foreign products became possible industrially with an easy access to them. From this, it can be seen that department stores were mediators of trends and the epicenter of popularizing exotic tastes.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.891-898
• /
• 2022

Purpose: There is not much time left for mandatory BIM implementation for all sectors and stages of the construction industry. Therefore, it is necessary to find a way to secure technology to substantially improve the productivity of BIM work. In the research, we proposed a method to automatically verify related construction standards for major objects produced by BIM modeling procedures so that engineers can verify construction standards in the BIM-based design process. Method: We defined a modeling work procedure for BIM-based road design work and prepared a method for constructing related design standards in a database. In addition, a process map for developing a BIM-based design basis review automation system was also presented. Result: A BIM-based design standard review automation module was developed using Civil3D and Dynamo. And it was confirmed by the test application that it is possible to quickly judge whether the BIM object manufactured in the design process conforms to the construction design standard. Conclusion: BIM-based design standard review automation technology can improve the productivity of BIM model production work and secure the quality of the BIM model.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.24 no.4
• /
• pp.11-25
• /
• 2022

Convergence, a universal phenomenon in modern society, takes place in various ways throughout society, and the concept of convergence can also be observed in fashion shows. The concept of convergence is actively emerging in terms of fashion show directing. The purpose of this study is to suggest the development of fashion show directing by analyzing the convergence characteristics of fashion show directing through a Louis Vuitton fashion show, and to provide data on convergence in fashion shows. The object of the study is the women's Paris Pret-a-porter and women's cruise collection presented at the Louis Vuitton fashion show. The research method integrated the criteria for analysis and the characteristics of fashion show production through previous studies and a literature review. The characteristics of convergence production in Louis Vuitton fashion shows were identifeid through literature and visual data. In this study, the convergence of the Louis Vuitton fashion shows were divided into four categories: genre integration, sensory synesthesia, perspective diversification, and media scalability. First, the integration of genres enhanced the brand image and effectively conveyed the concept of the show. Second, the synesthesia of the senses expanded communication with the audience and increased the audience's immersion. It has also become a new way to experience fashion shows in person. Third, the diversity of perspectives changed and diversified the way audiences experienced fashion shows. Fourth, the scalability of the media means various ways in which the audience can experience fashion shows. Through this, it is possible to effectively convey information and experiences about fashion shows to the audience.

• Korea Science and Art Forum
• /
• v.19
• /
• pp.601-612
• /
• 2015

Postmodernism has blurred the line between design and art. We would like to suggest a design case that took diversity in the modern era that harmonizes functionality and shape of the top board of a furniture and trend of the role of furniture and objet into consideration. This study aims to project a new role into space via convergence of objet that has aesthetic function and furniture design that plays practical role in space. Thus, furniture design attempts to combine ceramic and carpentry and demonstrate the value and potential the combination possesses. By creating a distinct design from previous furniture that had visual limitations with ceramic bridge that adopted existing piling method in ceramic design, we expect a fresh blend of furniture and space that encompasses a different sensation from color and texture of soil and glaze, unable to attain from simple wood.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.157-157
• /
• 2022

Recent decades have seen all over the world increasing drought in some regions and increasing flood in others. Climate change has been alarming in many regions resulting in degradation and diminution of available freshwater. The effect of global warming and overpopulation associated with increasing irrigated farming and valuable agricultural lands could be particularly disastrous for coastal areas like the one of Benin. The coastal region of Benin is under a heavy demographic pressure and was in the last decades the object of important urban developments. The present study aims to roughly study the general effect of climate change (Sea Level Rise: SLR) and groundwater pumping on Seawater intrusion (SWI) in Benin's coastal region. To reach the main goal of our study, the region aquifer system was built in numerical model using SEAWAT engine from Visual MODFLOW. The model is built and calibrated from 2016 to 2020 in SEAWAT, and using WinPEST the model parameters were optimized for a better performance. The optimized parameters are used for seawater intrusion intensity evaluation in the coastal region of Benin The simulation of the hydraulic head in the calibration period, showed groundwater head drawdown across the area with an average of 1.92m which is observed on the field by groundwater level depletion in hand dug wells mainly in the south of the study area. SWI area increased with a difference of 2.59km² between the start and end time of the modeling period. By considering SLR due to global warming, the model was stimulated to predict SWI area in 2050. IPCC scenario IS92a simulated SLR in the coastal region of Benin and the average rise is estimated at 20cm by 2050. Using the average rise, the model is run for SWI area estimation in 2050. SWI area in 2050 increased by an average of 10.34% (21.04 km²); this is expected to keep increasing as population grows and SLR.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.26 no.1
• /
• pp.61-76
• /
• 2024

The purpose of this study is the development of an experimental design that aims to implement three-dimensional fashion design by observing the human body, extracting and combining geometric shapes and forms, and focusing on attempts to decompose the geometry of the human body in art history. Considering the characteristics of fashion design, which inevitably reflect human images visually, this study considered works by deriving geometric shapes and forms of the human body and focusing on decomposition and combination to apply them to fashion design. The results obtained through the development of fashion design through decomposition and combination based on geometric human body analysis are as follows. First, geometric analysis of the human body as an object of expression continues from the history of Cubism to modern fashion design. Second, the geometric shapes of the human body that appear in contemporary fashion design maximize visual effects through three-dimensional composition, emphasizing simplicity while showing originality through various expressions. Third, when exploring the geometric shapes of a moving human body, it was possible to extract a wide variety of shapes and forms through drawing and simplifying the human body's movements. Fourth, the formative method of fashion design was introduced and used for the aesthetic combination of objects for fashion design through decomposition and combination. This study was able to show unique and diverse combinations of visually concise and ordered geometric shapes in the expression of fashion design by decomposing and combining them. The significance of these geometric forms is that they can diversify formative informativeness in the expression of fashion design with modern compositional beauty.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.77-84
• /
• 2024

In this paper, we propose a method for accurately and rapidly detecting defects in wire harnesses by utilizing computer vision to calculate six crucial measurement values: the length of crimped terminals, the dimensions (width) of terminal ends, and the width of crimped sections (wire and core portions). We employ Harris corner detection to locate object positions from two types of data. Additionally, we generate reference points for extracting measurement values by utilizing features specific to each measurement area and exploiting the contrast in shading between the background and objects, thus reflecting the slope of each sample. Subsequently, we introduce a method using the Euclidean distance and correction coefficients to predict values, allowing for the prediction of measurements regardless of changes in the wire's position. We achieve high accuracy for each measurement type, 99.1%, 98.7%, 92.6%, 92.5%, 99.9%, and 99.7%, achieving outstanding overall average accuracy of 97% across all measurements. This inspection method not only addresses the limitations of conventional visual inspections but also yields excellent results with a small amount of data. Moreover, relying solely on image processing, it is expected to be more cost-effective and applicable with less data compared to deep learning methods.