• 제목/요약/키워드: 영상 강화

Search Result 497, Processing Time 0.138 seconds

An Artificial Intelligence Approach to Waterbody Detection of the Agricultural Reservoirs in South Korea Using Sentinel-1 SAR Images (Sentinel-1 SAR 영상과 AI 기법을 이용한 국내 중소규모 농업저수지의 수표면적 산출)

  • Choi, Soyeon;Youn, Youjeong;Kang, Jonggu;Park, Ganghyun;Kim, Geunah;Lee, Seulchan;Choi, Minha;Jeong, Hagyu;Lee, Yangwon
    • Korean Journal of Remote Sensing
    • /
    • v.38 no.5_3
    • /
    • pp.925-938
    • /
    • 2022
  • Agricultural reservoirs are an important water resource nationwide and vulnerable to abnormal climate effects such as drought caused by climate change. Therefore, it is required enhanced management for appropriate operation. Although water-level tracking is necessary through continuous monitoring, it is challenging to measure and observe on-site due to practical problems. This study presents an objective comparison between multiple AI models for water-body extraction using radar images that have the advantages of wide coverage, and frequent revisit time. The proposed methods in this study used Sentinel-1 Synthetic Aperture Radar (SAR) images, and unlike common methods of water extraction based on optical images, they are suitable for long-term monitoring because they are less affected by the weather conditions. We built four AI models such as Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), and Automated Machine Learning (AutoML) using drone images, sentinel-1 SAR and DSM data. There are total of 22 reservoirs of less than 1 million tons for the study, including small and medium-sized reservoirs with an effective storage capacity of less than 300,000 tons. 45 images from 22 reservoirs were used for model training and verification, and the results show that the AutoML model was 0.01 to 0.03 better in the water Intersection over Union (IoU) than the other three models, with Accuracy=0.92 and mIoU=0.81 in a test. As the result, AutoML performed as well as the classical machine learning methods and it is expected that the applicability of the water-body extraction technique by AutoML to monitor reservoirs automatically.

An Essay on the Change of Jinju Sword Dance after being designated as an Important Intangible Cultural Asset (<진주검무> 중요무형문화재 지정 이후의 변화에 관한 소고)

  • Lee, Jong Sook
    • Korean Journal of Heritage: History & Science
    • /
    • v.49 no.1
    • /
    • pp.4-21
    • /
    • 2016
  • The purpose of this study is to investigate changes of Jinju Sword Dance, characteristics of the changes, and the current condition of its preservation and succession after the designation as the important intangible cultural property no. 12 in January 16th, 1967. In other words, this study understands the situation which has established the present state of after changes over generations. As of now. the year of 2015, the 3 generation holders have been approved since 1967. In 1967, 8 members of $1^{st}$ generation holders were selected from gisaengs of Gwonbeon. However, the succession training was incomplete due to conflicts among the holders, the deaths of some holders, and economic activities of the individuals. As the need of a pivot for succession training and activities was rising, Seong, Gye-Ok was additionally approved as the $2^{nd}$ generation holder on June $21^{st}$, 1978. Seong, Gye-Ok who had never been a gisaeng had dramatically changed with a lot of new attempts. After the death of Seong, Gye-Ok in 2009, Kim, Tae-Yeon and Yu, Yeong-Hee were approved as the $3^{rd}$ generation holders in February, 2010. Based on the resources including the "Cultural Research Reports of Important Intangible Cultural Properties" in 1966 and videos up to 2014, the changes of the dance and surroundings are as follow. 1. The formation of musical accompaniment has been changed during the 3 generations. In the video of the $1^{st}$ generation(in 1970), the performance lasted about 15 minutes, whereas the performance lasted 25 minutes in the video of the $2^{nd}$ generation. Yumbuldoduri rhythm was considered as Ginyumbul(Sangryeongsan) and played more slowly. The original dance requiring only 15 rhythms was extended to 39 rhythms to provide longer performance time. In the $3^{rd}$ generation, the dance recovered 15 rhythms using the term Ginyumbul. The facts that Yumbul was played for 3 minutes in the $1^{st}$ generation but for 5 minutes in the 3rd generation shows that there was tendency pursuing the slowness from the $2^{nd}$ generation. 2. For the composition of the Dance, the performance included additional 20 rhythms of Ginyumbul and Ah(亞)-shaped formation from the $2^{nd}$ generation. From the $3^{rd}$ generation, the performance excluded the formation which had no traditional base. For the movement of the Dance, the bridge poses of Ggakjittegi and Bangsukdoli have been visibly inflexible. Also, the extention of time value in 1 beat led the Dance less vibrant. 3. At the designation as an important intangible cultural property (in 1967), the swords with rotatable necks were used, whereas the dancers had been using the swords with non-rotatable necks since late 1970s when the $2^{nd}$ generation holder began to used them. The swords in the "Research Reports" (in 1966) was pointy and semilunar, whereas the straight swords are being used currently. The use of the straight swords can be confirmed from the videos after 1970. 4. There is no change in wearing Jeonlib, Jeonbok, and Hansam, whereas the arrangement of Saekdong of Hansam was different from the arrangement shown in the "Research Reports". Also, dancers were considered to begin wearing the navy skirts when the swords with non-rotatable necks began to be used. Those results showed that has been actively changed for 50 years after the designation. The $2^{nd}$ generation holder, Seong, Gye-Ok, was the pivot of the changes. However, , which was already designated as an important intangible cultural property, is considered to be only a victim of the change experiment from the project to restore Gyobang culture in Jinju, and it is a priority to conduct studies with historical legitimacy. First of all, the slowing beat should be emphasized as the main fact to reduce both the liveliness and dynamic beauty of the Dance.

Characteristic for Long-term Trends of Temperature in the Korean Waters (한국 연근해 수온의 시공간적 장기변동 특성)

  • Seong, Ki-Tack;Hwang, Jae-Dong;Han, In-Seong;Go, Woo-Jin;Suh, Young-Sang;Lee, Jae-Young
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.16 no.4
    • /
    • pp.353-360
    • /
    • 2010
  • The result of analysis of the observed temperature data by the Serial Oceanography Investigation of National Fisheries Research and Development Institute (NFRDI) during last 41 years from 1969 to 2008 showed that sea surface temperatures in the East, West and South Sea of Korea were clearly increased. In case of 100m depth, temperature was increased in the South Sea of Korea, but it was decreased in the East Sea. Especially, the temperature around the coastal area in the East Sea was significantly decreased by the spatial distribution of long-term change of temperature on 100m depth. It should lead to the decreasing trend in the long-term change of temperature on 100 m depth in the entire East Sea. The increasing trend was clearly larger in wintertime than in summertime by a factor of about 2 It means that the long-term increasing trend of sea surface temperature in the Korean Waters is usually caused by the distinctive increasing trend in wintertime. As the results of the analysis of air temperature and wind speed on the 6stations around the coastal area in the Korean Waters, air temperature was found to be continuously increased, but wind speed to be gradually decreased in winter. The weakness of vertical mixing by decreasing of wind speed caused to make the surface mixed layer shallow. it could be considered that the increasing trend of surface temperature was caused by weak mixing between surface and intermediate layers.

The Situation and the Tasks of UK Rail Privatization, Focusing on after the Hatfield Accident (영국 철도 민영화의 현황 및 과제 (Hatfield사고 이후의 변화를 중심으로))

  • Lee, Yong-Sang
    • Journal of Korean Society of Transportation
    • /
    • v.24 no.2 s.88
    • /
    • pp.91-100
    • /
    • 2006
  • This paper examines the situation and tasks of UK rail privatization, especially focusing on after the Hatfield rail accident. Earlier research which focused on the UK's Privatization had little knowledge of the explanations for recent changes. Moreover they had difficulty making a direct comparison between national rail and the privatized rail. Therefore we aye left without a good explanation which has a comprehensive perspective. I attempt to show the change in the rail privatization Process and its outcome, focusing on after the Hatfield rail accident. This Paper argues that the UK's vail privatization process has a regulatory framework which is too complicated with overlapping responsibilities that brought about inefficiency, increasing costs and a superficial safety regime. Especially the planning of rail and infrastructure maintenance did not come to play an appropriate role. However after 2000, the government took charge of setting the strategy for railways, and the Office of Rail Regulation covered safety performance and cost. explain that these changes present a good opportunity to solve the problem of passing the buck for poor performance. Through the analysis, I find that the passenger rail network is well-suited to deliver long distance business and commuters and that the subsidy from the government is decreasing. However, performance, for example punctuality and reliability. should be improved. Especially the Hatfield rail accident caused a reduction in the satisfaction of passengers. In future. the problems of rising costs and monopoly franchise system should be addressed.

A model for enhancing the academic excellence of adult college students (성인대학생의 학업수월성 강화를 위한 모형)

  • Kim, Eun Young;Kim, Jin Sook
    • The Journal of the Convergence on Culture Technology
    • /
    • v.5 no.2
    • /
    • pp.195-200
    • /
    • 2019
  • The purpose of this study is to present a model for enhancing the academic excellence of adult college students. For this purpose, 408 adult college students attending 2-year and 4-year colleges in Busan, Daegu, and Gyeongbuk were surveyed and analyzed. The components of the model are curriculum, educational methods, evaluation of education, educational administration, educational environment, and institutional support and the results are as follows. First, the curriculum preferred by adult college students was to acquire diverse academic knowledge for a degree, to acquire knowledge and skills to develop skills for the workplace, and to acquire new information and knowledge regarding issues in society as a whole. Second, the professors' qualification among the educational methods preferred by adult college students was professional competence of the professors based on their theoretical and practical skills. The preferred teaching methods were lecture, discussion, action learning, and the project learning method in that order and video and PowerPoint were preferred as effective teaching mediums. Third, the preferred course for adult college students is operated on weekends, and three years was preferred to get a bachelor's degree. The possible hours of learning per day is 3~6 hours, indicating the necessity of e-learning, B-learning, and prior learning experience recognition systems. Fourth, the education evaluation method preferred by adult college students was a compromise method which is a mixture of absolute evaluation and relative evaluation, and it also showed the need for Pass or Non Pass evaluation method. Fifth, the internal factors of college selection preferred by adult college students were the acquisition of new knowledge and skills, and the external factors were desire to receive many opportunities related to employment and job improvement. The classroom, which provides an effective environment, was a fixed seat classroom and an indoor classroom environment was emphasized for desired educational environment. Sixth, institutional support preferred by adult college students was computer-related programs and learning club support services.

Design and Implementation of Android-based Open U-Learning System for Improve Learning Effect : Focusing on 2009 revised science education courses (학습 효과 증진을 위한 안드로이드 기반의 개방형 U-러닝 시스템 설계 및 프로토타입 제작 : 2009년 개정 과학과 교육 과정 중심으로)

  • Kim, Youn-Soo;Lee, Ju-Hong
    • Journal of the Korea Society of Computer and Information
    • /
    • v.19 no.10
    • /
    • pp.135-149
    • /
    • 2014
  • This study proposed the ubiquitous learning system by finding the difficulties which students have in learning the course of science and analyzing the current learning applications that are used commercially. Through case studies, we found 4 problems. First, the request of long learning time by most of the existing video-based learning applications. Second, it is impossible to know their level of learning due to the lack of open learning contents. Third, it is difficult for learners to participate in interactive learning. Fourth, there are educational contents without considerations on the level of learners. To refine the difficulties due to these problems, we designed and implemented a new ubiquitous learning system which applies the small learning contents for short-term learning, open learning system and enhanced hierarchical learning contents. The system was implemented based on Android. It provides learners with useful science education. We conducted a questionnaire for third grade middle school students in order to show that the proposed system has a good educational effects. The questionnaire asks for the differences between the proposed ubiquitous learning system and the existing learning application. We concluded that the proposed system is better than the existing application by using t-test for improvement of learning effects using feedback with which students participate in interactive learning but not in unidirectional learning, and share the learning result.

The Effect of Motivation on Cyber Plagiarism in Using Social Media: The Focus of Subjective Norm's moderating Effect (소셜 미디어 사용에서 동기부여가 사이버 표절에 미치는 영향: 주관적 규범의 조절효과를 중심으로)

  • Kang, Sora;Han, Su Jin
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.17 no.6
    • /
    • pp.300-307
    • /
    • 2016
  • The development of computer-based information technology has led to the quantitative and qualitative growth of social media which have two sides; a positive one such as the generation and sharing of information and a negative one which includes cyber plagiarism and cyber bullying. This study seeks to understand which factors can lead to cyber plagiarism, which is the most prevalent form of unethical cyber behavior. We expected that the intrinsic and extrinsic motivations for using social media would have different effects on unethical cyber intention and that this relation between motivation and cyber unethical behavior would be moderated by the subjective norm. In order to obtain a better understanding of the relationships among the individual motivation, unethical cyber intention, and cyber plagiarism, information was obtained from 564 social media users. The respondents provided details of their experiences and attitudes regarding social media usage behavior and unethical cyber behavior. The results confirmed that extrinsic motivation significantly increases unethical intention and further leads to high levels of cyber plagiarism. The subjective norm plays a moderating role in the relationships between extrinsic motivation and unethical cyber intention. Based on the results, the theoretical and practical implications of the research findings are discussed, and recommendations for future research are provided.

Augmented Reality Game Interface Using Hand Gestures Tracking (사용자 손동작 추적에 기반한 증강현실 게임 인터페이스)

  • Yoon, Jong-Hyun;Park, Jong-Seung
    • Journal of Korea Game Society
    • /
    • v.6 no.2
    • /
    • pp.3-12
    • /
    • 2006
  • Recently, Many 3D augmented reality games that provide strengthened immersive have appeared in the 3D game environment. In this article, we describe a barehanded interaction method based on human hand gestures for augmented reality games. First, feature points are extracted from input video streams. Point features are tracked and motion of moving objects are computed. The shape of the motion trajectories are used to determine whether the motion is intended gestures. A long smooth trajectory toward one of virtual objects or menus is classified as an intended gesture and the corresponding action is invoked. To prove the validity of the proposed method, we implemented two simple augmented reality applications: a gesture-based music player and a virtual basketball game. In the music player, several menu icons are displayed on the top of the screen and an user can activate a menu by hand gestures. In the virtual basketball game, a virtual ball is bouncing in a virtual cube space and the real video stream is shown in the background. An user can hit the virtual ball with his hand gestures. From the experiments for three untrained users, it is shown that the accuracy of menu activation according to the intended gestures is 94% for normal speed gestures and 84% for fast and abrupt gestures.

  • PDF

Systematic Approach to The Extraction of Effective Region for Tongue Diagnosis (설진 유효 영역 추출의 시스템적 접근 방법)

  • Kim, Keun-Ho;Do, Jun-Hyeong;Ryu, Hyun-Hee;Kim, Jong-Yeol
    • Journal of the Institute of Electronics Engineers of Korea SC
    • /
    • v.45 no.6
    • /
    • pp.123-131
    • /
    • 2008
  • In Oriental medicine, the status of a tongue is the important indicator to diagnose the condition of one's health like the physiological and the clinicopathological changes of internal organs in a body. A tongue diagnosis is not only convenient but also non-invasive, and therefore widely used in Oriental medicine. However, the tongue diagnosis is affected by examination circumstances like a light source, patient's posture, and doctor's condition a lot. To develop an automatic tongue diagnosis system for an objective and standardized diagnosis, segmenting a tongue region from a facial image captured and classifying tongue coating are inevitable but difficult since the colors of a tongue, lips, and skin in a mouth are similar. The proposed method includes preprocessing, over-segmenting, detecting the edge with a local minimum over a shading area from the structure of a tongue, correcting local minima or detecting the edge with the greatest color difference, selecting one edge to correspond to a tongue shape, and smoothing edges, where preprocessing consists of down-sampling to reduce computation time, histogram equalization, and edge enhancement, which produces the region of a segmented tongue. Finally, the systematic procedure separated only a tongue region from a face image with a tongue, which was obtained from a digital tongue diagnosis system. Oriental medical doctors' evaluation for the results illustrated that the segmented region excluding a non-tongue region provides important information for the accurate diagnosis. The proposed method can be used for an objective and standardized diagnosis and for an u-Healthcare system.

Lived Experience of Suffering For Family of Victim with Sewol-ho Ferry Accident: Applied to Parse's Human Becoming Methodology (세월호 사건 피해자 가족의 고통 체험에 관한 연구: Parse의 인간되어감 연구방법을 적용)

  • Kim, Jung-Mi
    • The Journal of Korean society of community based occupational therapy
    • /
    • v.4 no.1
    • /
    • pp.59-73
    • /
    • 2014
  • Objective : The purpose of this study is to understand Lived Experience of Suffering for family of victim with Sewol-ho ferry accident and to suggest the necessity of mental health occupational therapy regarding of psychological trauma of family of victim. Methods : This study was applied with Parse's Human becoming research method to recognize experience pain for 5 objects losing family with with Sewol-ho ferry accident. According to Parse's research mothod, secondary data, documentary video about experience pain of family of victim with Sewol-ho ferry accident was selected and analyzed. Results : Three core concept for lived experience of suffering of family with victim with Sewol-ho ferry accident as below statements. 1. Despair and sadness losing family, 2. Impotent feeling and guilty conscience breaking down daily life, 3. Seeking relief from suffering for remaining family. Although there were extreme impotent feeling of losing family with Sewol-ho ferry accident, structural conversion presented as process with denial reality which do not want to accept a death in the family and standing for remaining family. The conceptual integration was expressed to powering from valuing and languaging to connection-separation, revealing-concealingl. Conclusion : Family of victim with Sewol-ho ferry accident is losing meaning of life the goal of life with impotent feeling, despair and depression. It is urgently needed for mental health occupational therapy program to restore disruptive everyday activity and participation in community by developing occupational therapy program through meaningful occupation to family of victim.

  • PDF