• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1111-1123
• /
• 2023

In recent times, semantic image segmentation methods using deep learning models have been widely used for monitoring changes in surface attributes using remote sensing imagery. To enhance the performance of various UNet-based deep learning models, including the prominent UNet model, it is imperative to have a sufficiently large training dataset. However, enlarging the training dataset not only escalates the hardware requirements for processing but also significantly increases the time required for training. To address these issues, transfer learning is used as an effective approach, enabling performance improvement of models even in the absence of massive training datasets. In this paper we present three transfer learning models, UNet-ResNet50, UNet-VGG19, and CBAM-DRUNet-VGG19, which are combined with the representative pretrained models of VGG19 model and ResNet50 model. We applied these models to building extraction tasks and analyzed the accuracy improvements resulting from the application of transfer learning. Considering the substantial impact of learning rate on the performance of deep learning models, we also analyzed performance variations of each model based on different learning rate settings. We employed three datasets, namely Kompsat-3A dataset, WHU dataset, and INRIA dataset for evaluating the performance of building extraction results. The average accuracy improvements for the three dataset types, in comparison to the UNet model, were 5.1% for the UNet-ResNet50 model, while both UNet-VGG19 and CBAM-DRUNet-VGG19 models achieved a 7.2% improvement.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.4
• /
• pp.145-160
• /
• 2023

The purpose of this study was to compare and analyze diurnal thermal environments using Unmanned Aerial Vehicles(UAV)-derived physical parameters(NDVI, SVF) and ENVI-met modeling. The research findings revealed significant correlations, with a significance level of 1%, between UAV-derived NDVI, SVF, and thermal environment elements such as S↑, S↓, L↓, L↑, Land Surface Temperature(LST), and Tmrt. In particular, NDVI showed a strong negative correlation with S↑, reaching a minimum of -0.52^** at 12:00, and exhibited a positive correlation of 0.53^** or higher with L↓ at all times. A significant negative correlation of -0.61^** with LST was observed at 13:00, suggesting the high relevance of NDVI to long-wavelength radiation. Regarding SVF, the results showed a strong relationship with long-wave radiative flux, depending on the SVF range. These research findings offer an integrated approach to evaluating thermal comfort and microclimates in urban areas. Furthermore, they can be applied to understand the impact of urban design and landscape characteristics on pedestrian thermal comfort.

• Journal of Industrial Convergence
• /
• v.22 no.1
• /
• pp.105-115
• /
• 2024

This study aimed to analyze the impact of mental strength on the competitive performance of student Taekwondo sparring athletes. A total of 343 middle school, high school, and university students registered as Taekwondo sparring athletes with the Korea Taekwondo Association were conveniently sampled. The Mental Toughness Test developed by Loehr was utilized after expert consultations. Data analysis involved t-tests and one-way ANOVA to assess the levels of mental strength sub-factors based on general characteristics, followed by post hoc tests using the Schéffe method for intergroup comparisons. Correlation analysis and multiple regression were conducted to examine the relationship between sub-factors of mental strength and competitive ability. The results indicated significant differences in mental strength sub-factors-confidence, level of awakening regulation, visualization and mental imagery regulation, motivation level, positive energy, and attitude control-based on gender and age among Taekwondo sparring student athletes. In terms of perceived competitive ability, significant differences were found based on age and sports experience. Consequently, beyond psychological training, the study revealed that age and diverse experiences positively influence specific aspects of mental strength among Taekwondo sparring student athletes. Therefore, coaching and training for these athletes, particularly during middle and high school years, should incorporate psychological aspects alongside diverse competition experiences and training to help overcome performance evaluation anxieties during matches.

• Korean Journal of Remote Sensing
• /
• v.40 no.3
• /
• pp.275-284
• /
• 2024

Monitoring crop growth changes and water content is crucial in the agricultural sector. This study utilized drones equipped with Short Wavelength Infrared (SWIR) sensors, sensitive to moisture changes, to observe soybeans' growth and water content variations. We confirmed that as soybeans grow more vigorously, their water content increases and differences in irrigation levels lead to decreases in vegetation and moisture indices. This suggests that waterlogging slows down soybean growth and reduces water content, highlighting the importance of detailed monitoring of vegetation and moisture indices at different growth stages to enhance crop productivity and minimize damage from waterlogging. Such monitoring could also preemptively detect and prevent the adverse effects of moisture changes, such as droughts, on crop growth. By demonstrating the potential for early diagnosis of moisture stress using drone-based SWIR sensors, this research suggests improvements in the efficiency of large-scale crop management and increases in yield, contributing to agricultural production.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.6
• /
• pp.135-154
• /
• 2023

Urban wetlands provide various ecosystem services and are subject to restoration and creation projects due to their increased value in the context of climate change. However, the vegetation structure of wetlands is sensitive to environmental changes, including artificial disturbances, and requires continuous maintenance. In this study, we conducted a vegetation survey of three wetlands created as part of a project to restore urban degraded natural ecosystems and monitored the quantitative changes in wetland vegetation structure using an unmanned aerial vehicle. The vegetation survey revealed 73 species in Incheon Yeonhui wetland, and the change in vegetation composition based on wetland occurrence frequency was 11.5% on average compared to the 2018 vegetation survey results. The vegetation survey identified 44 species in Busan Igidae wetland, and the proportion of species classified as obligate upland plants was the highest at 48.8% among all plants, while the proportion of naturalized plants accounted for 15.9% of all plants. The open water surface area decreased from 10% in May 2019 to 6.7% in May 2020. Iksan Sorasan wetland was surveyed and 44 species were confirmed, and it was found that the proportion of facultative wetland plant decreased compared to the 2018 vegetation survey results, and the open water surface area increased from 0.4% in May 2019 to 4.1% in May 2020. The results of this study showed that wetlands with low artificial management intensity exhibited a tendency for stabilization of vegetation structure, with a decrease in the proportion of plants with high wetland occurrence frequency and a relatively small number of new species. Wetlands with high artificial management intensity required specific management, as they had a large change in vegetation structure and a partially high possibility of new invasion. We reaffirmed the importance of continuous monitoring of vegetation communities and infrastructure for wetlands considering the function and use of urban wetlands, and restoration stages. These research results suggest the need to establish a sustainable wetland maintenance system through the establishment of long-term maintenance goals and monitoring methods that consider the environmental conditions and vegetation composition of wetlands.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.28 no.12 s.138
• /
• pp.1583-1595
• /
• 2004

Simon and Sullivan(l993) estimated that clothing and textile related brand equity had the highest magnitude comparing any other industry category. It reflects that fashion brands reinforce the symbolic, social values and emotional characteristics being different from generic brands. Recently, Kim and Lim(2002) developed a fashion brand equity scale to measure a brand's psychometric properties. However, they suggested that additional psychometric tests were needed to compare the relative magnitude of each brand's equity. The purpose of this study was to recognize the psychometric constructs of fashion brand equity and validate Kim and Lim's fashion brand equity scale using the measurement invariance test of cross-group comparison. First, we identified the constructs of fashion brand equity using confirmatory factor analysis through structural equation modeling. Second, we compared the relative magnitude of two brands' equity using the measurement invariance test of multi-group simultaneous factor analysis. Data were collected at six major universities in Seoul, Korea. There were 696 usable surveys for data analysis. The results showed that fashion brand equity was comprised of 16 items representing six dimensions: customer-brand resonance, customer feeling, customer judgment, brand imagery, brand performance and brand awareness. Also, we could support the measurement invariance of two brands' equities by configural and metric invariance tests. There were significant differences in five constructs' mean values. The greatest difference was in customer feeling; the smallest, in customer judgment.

• Cartoon and Animation Studies
• /
• s.37
• /
• pp.509-537
• /
• 2014

This paper proposes 'postfilimc metamorphosis' and 'reanimation' as two concepts that aim at giving account to the aesthtetic tendencies and genealogies of what Suzanne Buchan calls 'pervasive animation', a category that refers to the unprecedented expansion of animation's formal, technological and experiential boundaries. Buchan's term calls for an interdisciplinary approach to animation by highlighting a range of phenomena that signal the growing embracement of the images and media that transcend the traditional definition of animation, including the lens-based live-action image as the longstanding counterpart of the animation image, and the increasing uses of computer-generated imagery, and the ubiquity of various animated images dispersed across other media and platforms outside the movie theatre. While Buchan's view suggests the impacts of digital technology as a determining factor for opening this interdisciplinary, hybrid fields of 'pervasive animation', I elaborate upon the two concepts in order to argue that the various forms of metamorphorsis and motion found in these fields have their historical roots. That is, 'postfilmic metamorphosis' means that the transformative image in postfimic media such as video and the computer differs from that in traditional celluloid-based animation materially and technically, which demands a refashioned investigation into the history of the 'image-processing' video art which was categorized as experimental animation but largely marginalized. Likewise, 'reanimation' cne be defined as animating the still images (the photographic and the painterly images) or suspending the originally inscribed movement in the moving image and endowing it with a neewly created movement, and both technical procedues, developed in experimental filmmaking and now enabled by a variety of moving image installations in contemporary art, aim at reconsidering the borders between stillness and movement, and between film and photography. By discussing a group of contemporary moving image artworks (including those by Takeshi Murata, David Claerbout, and Ken Jacobs) that present the aesthetic features of 'postfilmic metamorphosis' and 'reanimation' in relation to their precursors, this paper argues that the aesthetic implications of the works that pertain to 'pervasive animation' lie in their challenging the tradition dichotomies of the graphic/the live-action images and stillness/movement. The two concepts, then, respond to a revisionist approach to reconfigure the history and ontology of other media images outside the traditional boundaries of animation as a way of offering a refasioned understanding of 'pervasive animation'.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_3
• /
• pp.1235-1249
• /
• 2019

Kilauea Volcano is one of the most active volcano in the world. In this study, we used the ALOS-2 PALSAR-2 satellite imagery to measure the surface deformation occurring near the summit of the Kilauea volcano from 2015 to 2017. In order to measure two-dimensional surface deformation, interferometric synthetic aperture radar (InSAR) and multiple aperture SAR interferometry (MAI) methods were performed using two interferometric pairs. To improve the precision of 2D measurement, we compared root-mean-squared deviation (RMSD) of the difference of measurement value as we change the effective antenna length and normalized squint value, which are factors that can affect the measurement performance of the MAI method. Through the compare, the values of the factors, which can measure deformation most precisely, were selected. After select optimal values of the factors, the RMSD values of the difference of the MAI measurement were decreased from 4.07 cm to 2.05 cm. In each interferograms, the maximum deformation in line-of-sight direction is -28.6 cm and -27.3 cm, respectively, and the maximum deformation in the along-track direction is 20.2 cm and 20.8 cm, in the opposite direction is -24.9 cm and -24.3 cm, respectively. After stacking the two interferograms, two-dimensional surface deformation mapping was performed, and a maximum surface deformation of approximately 30.4 cm was measured in the northwest direction. In addition, large deformation of more than 20 cm were measured in all directions. The measurement results show that the risk of eruption activity is increasing in Kilauea Volcano. The measurements of the surface deformation of Kilauea volcano from 2015 to 2017 are expected to be helpful for the study of the eruption activity of Kilauea volcano in the future.

• The Korean Journal of Air & Space Law and Policy
• /
• v.20 no.1
• /
• pp.87-107
• /
• 2005

Land Remote Sensing' is defined as the science (and to some extent, art) of acquiring information about the Earth's surface without actually being in contact with it. Narrowly speaking, this is done by sensing and recording reflected or emitted energy and processing, analyzing, and applying that information. Remote sensing technology was initially developed with certain purposes in mind ie. military and environmental observation. However, after 1970s, as these high-technologies were taught to private industries, remote sensing began to be more commercialized. Recently, we are witnessing a 0.61-meter high-resolution satellite image on a free market. While privatization of land remote sensing has enabled one to use this information for disaster prevention, map creation, resource exploration and more, it can also create serious threat to a sensed nation's national security, if such high resolution images fall into a hostile group ie. terrorists. The United States, a leading nation for land remote sensing technology, has been preparing and developing legislative control measures against the remote sensing industry, and has successfully created various policies to do so. Through the National Oceanic and Atmospheric Administration's authority under the Land Remote Sensing Policy Act, the US can restrict sensing and recording of resolution of 0.5 meter or better, and prohibit distributing/circulating any images for the first 24 hours. In 1994, Presidential Decision Directive 23 ordered a 'Shutter Control' policy that details heightened level of restriction from sensing to commercializing such sensitive data. The Directive 23 was even more strengthened in 2003 when the Congress passed US Commercial Remote Sensing Policy. These policies allow Secretary of Defense and Secretary of State to set up guidelines in authorizing land remote sensing, and to limit sensing and distributing satellite images in the name of the national security - US government can use the civilian remote sensing systems when needed for the national security purpose. The fact that the world's leading aerospace technology country acknowledged the magnitude of land remote sensing in the context of national security, and it has made and is making much effort to create necessary legislative measures to control the powerful technology gives much suggestions to our divided Korean peninsula. We, too, must continue working on the Korea National Space Development Act and laws to develop the necessary policies to ensure not only the development of space industry, but also to ensure the national security.

• Journal of radiological science and technology
• /
• v.40 no.2
• /
• pp.245-251
• /
• 2017

This study measured the exposure dose during abdominal-pelvic CT exam which occupies 70% of CT exam and tried to propose a protocol for optimized exposure dose in abdomen and pelvis without affecting the imagery interpretation. The study scanned abdomen-pelvis using the current clinical scan method, the 120 kVp, auto exposure control(AEC), as 1 phase. As for the newly proposed 2 phase scan method, the study divided into 1 phase abdomen exam and 2 phase pelvis exam and each conducted tube voltage 120 kVp, AEC for abdomen exam, and fixed tube current method in 120 kVp, 100, 150, 200, 250, 300, 350, 400 mA for pelvis exam. The exposure dose value was compared using $CTDI_{VOL}$, DLP value measured during scan, and average value of CT attenuation coefficient, noise, SNR from each scan image were obtained to evaluate the image. As for the result, scanning of 2 phase showed significant difference compared to 1 phase. In $CTDI_{VOL}$ value, the 2 phase showed 26% decrease in abdomen, 1.8~59.5% decrease in pelvis for 100~250 mA, 12.7%~30% increase in pelvis for 300~400 mA. Also, DLP value showed 53% decrease in abdomen and 41~81% decrease in pelvis when scanned by 2 phase compared to 1 phase, but it was not statistically significant. As for the SNR, when scanning 2 phase close to heart, scanning 1 phase close to pelvis, scanning and scanning 1 phase at upper and lower abdomen, it was higher when scanning 2 phase for 200~250 mA. Also, the CT number and noise was overall similar, but the noise was high close to pelvis. However, when scanning 2 phase for 250 mA close to pelvis, the noise value came out similar to 1 phase, and did not show statistically significant difference. It seems when separating pelvis to scan in 250 mA rather than 400 mA in 1 phase as before, it is expected to have reduced effect of exposure dose without difference in the quality of image. Thus, for patients who often get abdominal-pelvic CT exam, fertile women or children, this study proposes 2 phase exam for smaller exposure dose with same image quality.