• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4420-4438
• /
• 2021

Image dehazing is an ill-posed problem which is far from being solved. Traditional image dehazing methods often yield mediocre effects and possess substandard processing speed, while modern deep learning methods perform best only in certain datasets. The haze removal effect when processed by said methods is unsatisfactory, meaning the generalization performance fails to meet the requirements. Concurrently, due to the limited processing speed, most dehazing algorithms cannot be employed in the industry. To alleviate said problems, a lightweight fast dehazing network based on a multiple scale-patch framework (MSP) is proposed in the present paper. Firstly, the multi-scale structure is employed as the backbone network and the multi-patch structure as the supplementary network. Dehazing through a single network causes problems, such as loss of object details and color in some image areas, the multi-patch structure was employed for MSP as an information supplement. In the algorithm image processing module, the image is segmented up and down for processed separately. Secondly, MSP generates a clear dehazing effect and significant robustness when targeting real-world homogeneous and nonhomogeneous hazy maps and different datasets. Compared with existing dehazing methods, MSP demonstrated a fast inference speed and the feasibility of real-time processing. The overall size and model parameters of the entire dehazing model are 20.75M and 6.8M, and the processing time for the single image is 0.026s. Experiments on NTIRE 2018 and NTIRE 2020 demonstrate that MSP can achieve superior performance among the state-of-the-art methods, such as PSNR, SSIM, LPIPS, and individual subjective evaluation.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.311-323
• /
• 2023

Ever since ancient times, earthquakes have been a major threat to the civil infrastructures and the safety of human beings. The majority of casualties in earthquake disasters are caused by the damaged civil infrastructures but not by the earthquake itself. Therefore, the efficient and accurate post-earthquake assessment of the conditions of structural damage has been an urgent need for human society. Traditional ways for post-earthquake structural assessment rely heavily on field investigation by experienced experts, yet, it is inevitably subjective and inefficient. Structural response data are also applied to assess the damage; however, it requires mounted sensor networks in advance and it is not intuitional. As many types of damaged states of structures are visible, computer vision-based post-earthquake structural assessment has attracted great attention among the engineers and scholars. With the development of image acquisition sensors, computing resources and deep learning algorithms, deep learning-based post-earthquake structural assessment has gradually shown potential in dealing with image acquisition and processing tasks. This paper comprehensively reviews the state-of-the-art studies of deep learning-based post-earthquake structural assessment in recent years. The conventional way of image processing and machine learning-based structural assessment are presented briefly. The workflow of the methodology for computer vision and deep learning-based post-earthquake structural assessment was introduced. Then, applications of assessment for multiple civil infrastructures are presented in detail. Finally, the challenges of current studies are summarized for reference in future works to improve the efficiency, robustness and accuracy in this field.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.11 no.1
• /
• pp.3-19
• /
• 2009

The purpose of this study was to systemize the 'Eagi(理氣)' theory in Feng Shui which has been neglected in Korea because of its difficulties in the current Feng Shui theory and to make it easier to apply in the art of placement. The study also analysed the characteristics of the location of a sample village in terms of Feng Shui. Besides the placement analysis, the interpretation of the Yangtaek(陽宅) theory was analysed on the layout of the outdoor space of the building. As the initial step, various theories about Feng Shui were investigated. Based on those, the framework of the Feng Shui theory was summarized for application to the case study. Yangtaeksamyo(陽宅三要) was referred to for consideration of Feng Shui theory outside the residential buildings. At the same time, configurational analysis of the ground was carried out with the naked eye and actual measurements were taken using a specific compass(佩鐵). The results were summarized as follows : First, the 'Eagi' theory in Feng Shui, which finds a 'lucky site(穴)' selects the 'geomagnetic aspect(坐向)' by analyzing the natural forces of wind and water. In this theory, the aspect was regarded of most importance. 'Yangtaek Feng Shui (陽宅風水)' was the theory that people's ups and downs depends on the direction of the place where they live on, and was developed on the basis of 'I ching(周易)'. Second, the village and the house in the case study have been considered as lucky places from old times and this was equally verified by the 'Eagi (理氣)' theory and the "Yangtaek (陽宅)' theory.

• Journal of the Korean Institute of Rural Architecture
• /
• v.25 no.2
• /
• pp.43-50
• /
• 2023

This study is an architectural and landscaping analysis view to rural landscape paintings painted by Vincent van Gogh in the late 19th century. The purpose of this research is to discover the expressive techniques of Western art that Van Gogh's landscape paintings have, and to understand the characteristics of the architectural object in his landscape paintings from February 1888 to April 1889 in Arles, southern France. The method of this study is to analyze the landscape paintings of Van Gogh painted during 15 months in Arles. Among the total paintings in Arles, 47% of the paintings he made were landscapes. The following conclusions have three views. First, Vincent van Gogh was born into a Protestant family in the Netherlands and become an artist in his late twenties. While living in Arles, he painted prolific landscapes. Farming, farmers, and rural area related to normal living are the main subjects of paintings. It can be seen as showing the view that everyday life is sublime and should be included as a unitary value. Second, Gogh's rural landscape paintings were painted with linear and aerial perspective with other the expressive techniques, and plane painting structure that leads to two dimension. Third, from an architectural point of view, Van Gogh's paintings depicted simple vernacular architecture such as traditional rural house, mas, thatched houses, and mills in southern France. This means the normal value of the rural landscape through the eyes of the painter.

• Conservation Science in Museum
• /
• v.29
• /
• pp.111-132
• /
• 2023

Terahertz radiation cannot pass through metal and therefore reflect and return most signals. Utilizing this property, this study analyzed information on paintings to verify the usage of metal materials on paintings and the scope of their application. First, the study tested specimens of metal-based pigments and synthetic pearl pigments with metallic colors and textures in order to compare basic characteristics of terahertz images, such as signal severance caused by metallic substances, traits reflected in cross-section images, and high degree of reflection. Subsequently, based on the collected information, the study diagnosed various types of paintings including Korean traditional paintings and oil paintings using the terahertz imaging technique to confirm the usage of metal-based pigments in the inner layers of paintings and their scope of application. The terahertz imaging technique could has the potential to provide scientific evidence for previously-undiscovered information and art-historical records about various types of paintings that used metalbased pigments, thereby rendering significant utility for the conservation and authentication of paintings.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.6 no.6
• /
• pp.403-412
• /
• 2016

As transaction and investment using technology are vitalized, the need for objective standards for the technology is increasing. Current technology value evaluation system is limited lacking reliability and objectivity. Besides the traditional evaluation methodology which are market approach, income approach and cost approach other diverse evaluation methodology such as real option method and royalty calculation method are being studied; however currently there are no dominant evaluation methodology in the market. Same value evaluation system cannot be applied between similar technologies because value of technology is relatively decided based on the target. Approaching through collective intelligence and crowd sourcing, in meaning of majority participant's decision can make objective and better result than handful of experts, suggest alternative to problems of such matter above. By grafting the four types of crowd sourcing model which are Wisdom, Voting, Funding and Creation, this paper will discuss the ways to enhance the objectivity of technology evaluation through direct evaluation utilizing expert group and the public's indirect evaluation.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.3
• /
• pp.401-410
• /
• 2017

Augmented reality game has differences with traditional games in the way what it includes physical risks happened in the real world. Although accidents related to Pokemon Go are increasing, academic discussions on the issues are rare. Thus, this study explores risk types caused by the augmented reality game and examined how perception of the risks affect usage intention on the game. This study also provides the research implications through comparative analysis between youth group who generally has the tendency toward game addiction and older group. According to the results, teenagers had less usage intention when perceived financial risk increase. In case of over twenty, time risk had negative relationship with usage intention. Physical risk had no significant effect on usage intention for teenagers, but positive relationship was observed in case over twenty. These results imply the necessity of an appropriate regulation for safe game play.

• Design Convergence Study
• /
• v.14 no.5
• /
• pp.31-45
• /
• 2015

Recently, due to the development of interactive media, Interactive Typography, which explores user input and interaction is under development. Unlike traditional typography which has a fixed nature, the flexible and fluid nature of Interactive Typography and Interactive System, enables diverse results. In this study, I have developed an Interactive Typography art piece based on theoretical research. By reviewing books, papers and articles, I have tried to define the meaning and characteristics of Interactive Typography. In understanding the concept of Interactive System, I have borrowed the concept of mathematical function. Based on the research, I have designed and developed an Interactive Typography piece, 'Interactive floral type' by using Adobe flash action script. This piece explores the beautiful shape of each alphabet letters and transforms individual character into a 'flower' shape through user's mouse and keyboard input. Depending on the input the size, color, and layout and motion of text changes in real time to change the letters into beautiful flowers.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.7
• /
• pp.719-728
• /
• 2018

Each country has its preferred image and how to convey it effectively. The study aims to find traditional Korean makeup methods and ways to effectively convey a preferred image. Among the ancient manuscripts of Joseon Dynasty, the book " Galgap Collection " has ten ancestors who express their favorite eyebrows in the form of a grandfather. In this study, we applied tens of thousands of words to the actual model to solve the problem and make up the methods of literature, the Internet, and example. The model stimuli were measured by conducting a street experiment of 10 makeup experts and 70 men and women's blinds. The result was that the " Gaewon- .aemi " type seemed to be the best, attractive and most consistent with the shape of the thinking eyebrows and the current fashion of eyebrows. In a variety of nonverbal ways expressed in the classics, the study looked at ways to use visual poetry to communicate effectively. This research will help transform design ideas and help understand cultural trends of different times.