• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2008-2019
• /
• 1999

As computing technologies are rapidly progressed and widely used, the needs of high quality information have been increased. To satisfy these needs, it is essential to develop a system which can provide an efficient storing, managing and retrieving mechanism of complex multimedia data, esp. video data. In this paper, we propose a metadata model which can support content-based retrieval of video data. And we design and implement an integrated user interface for querying and browser for content-based retrieval in video database which can efficiently access and browse the video clip that user want to see. Proposed query processor and browser can support various user queries by integrating image feature, spatial temporal feature and annotation. Our system supports structure browsing of retrieved result, so users can more exactly and efficiently access relevant video clip. Without browsing the whole video clip, users can know the contents of video by seeing the storyboard. This storyboard facility makes users know more quickly the content of video clip.

• Composites Research
• /
• v.23 no.6
• /
• pp.1-6
• /
• 2010

The electrical conductivity of carbon-fiber reinforced plastics (CFRP's) has been improved by indium-tin oxide (ITO) nano-particle coating on carbon fibers for the purpose of lightning strike protection of composite fuselage skins. ITO nano-particles were coated on the surface of carbon fibers by spraying the colloidal suspension with 10~40% ITO content. The electrical conductivity of the CFRP has been increased more than three times after ITO coating, comparable to or higher than that of B-787 composite fuselage skins with metal wire-meshes on the outer surface, without sacrificing the tensile property due to the existence of nano-particles at fiber-matrix interface. The damage area by the simulated lightning strike was also verified for different materials and conditions by using ultrasonic C-scan image. As the electrical conductivity of 40% nano-ITO coated sample surpass that of the B-787 sample, the damage area by lightning strike also appeared comparable to that of the materials currently employed for composite fuselage construction.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2010.02a
• /
• pp.120-120
• /
• 2010

최근 투명전도성 산화물(Transparent Conductive Oxide, TCO) 박막은 액정 표시소자(LCD), 플라즈마 디스플레이 패널(PDP), 압전소자 및 태양전지의 투명소자로 사용되어지고 있다. 현재 가장 널리 사용되어지고 있는 투명전극물질인 인듐주석산화물(indium tin oxide, ITO)은 낮은 비저항과 높은 투과율을 가지고 있지만, 높은 원자재의 가격 및 수소플라즈마 처리시 In과 Sn이 환원되어 전기적, 광학적으로 불안정한 문제점들이 지적되고 있다. 이러한 문제점들을 해결하기 위해 최근 적외선 및 가시광선 영역에서 높은 투과도 및 전기 전도성과 수소플라즈마에 대한 화학적 안정성을 갖는 ZnO를 기반으로 3족 원소를 첨가한 새로운 투명 전도막에 대한 연구가 활발하다. 본 연구에서는 RF-Magnetron Sputtering법을 이용하여 $Ga_2O_3$ 혼합비에 따라 제작된 ZnO(GZO) 박막들의 전기적, 광학적, 구조적인 특성들을 분석하였다. 측정결과, $Ga_2O_3$의 첨가량이 7 wt.%인 GZO 박막이 가시광선영역에서 80%이상의 높은 투과율과 $50.5\;\Omega/\Box$의 가장 낮은 면저항을 나타내었다. 이는 Ga원소가 다른 3족 원소와 격자결합을 비교할 때, 이온의 크기가 Zn원소와 비슷하여 최적화된 혼합율을 가지는 경우 격자결합을 최소화시켜 캐리어 밀도의 증가로 인해 높은 전도성을 가지며, 고온에서도 전기적 특성 및 내구성이 향상되기 때문이다. 또한 기판온도에 따른 열처리 특성으로서 기판의 온도를 $100^{\circ}{\sim}400^{\circ}C$까지 변화를 주어 실험하였다. X-선 회절패턴 분석결과 기판온도가 증가함에 따라 ZnO (002) 방향이 감소하는 반면 ZnO(103) 방향이 증가하였으며, 기판온도가 $300^{\circ}C$ 일 때 $17.1\;\Omega/\Box$의로 가장 낮은 면저항이 나타났다. 이는 SEM 이미지를 분석한 결과, 실온에서 제작된 박막과 비교해 300 에서 증착된 GZO 박막이 결정립의 크기가 크고 밀도도 조밀해져 전하의 이동도가 향상되었기 때문이다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.15-21
• /
• 2023

This paper is a study on the development of an artificial intelligence model that recognizes a hole cup on a golf green. A CNN-based object detection algorithm was used to recognize the hole cup on the green. Also, Apple's CreateML was used to create a model of the object detection algorithm. This paper created a JSON file with 120 training images and annotations to meet the needs of CreateML. In addition, for more accurate learning, data amplification algorithm was used for learning data and 288 learning data were used for learning. By changing the Iterations, Batch size, and Grid size required by CreateML, we found parameter values that improve the performance of the model. A prototype app was developed by applying the developed model, and performance was measured on an actual golf course green using the prototype app. As a result of the measurement, it was found that the hole cup was accurately recognized within 10m, which is the typical golfer's putting distance.

• Transactions on Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.17-20
• /
• 2024

This paper presents a novel lightweight object detection model tailored for low-powered edge devices, addressing the limitations of traditional resource-intensive computer vision models. Our proposed detector, inspired by the Single Shot Detector (SSD), employs a compact yet robust network design. Crucially, it integrates an 'enhancer block' that significantly boosts its efficiency in detecting smaller objects. The model comprises two primary components: the Light_Block for efficient feature extraction using Depth-wise and Pointwise Convolution layers, and the Enhancer_Block for enhanced detection of tiny objects. Trained from scratch on the Udacity Annotated Dataset with image dimensions of 300x480, our model eschews the need for pre-trained classification weights. Weighing only 5.5MB with approximately 0.43M parameters, our detector achieved a mean average precision (mAP) of 27.7% and processed at 140 FPS, outperforming conventional models in both precision and efficiency. This research underscores the potential of lightweight designs in advancing object detection for edge devices without compromising accuracy.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.50 no.6
• /
• pp.42-57
• /
• 2022

This study aims to create a basic model for classifying the activity photos that urban park users shared on social media using Deep Learning through Artificial Intelligence. Regarding the social media data, photos related to urban parks were collected through a Naver search, were collected, and used for the classification model. Based on the indicators of Naturalness, Potential Attraction, and Activity, which can be used to evaluate the characteristics of urban parks, 21 classification categories were created. Urban park photos shared on Naver were collected by category, and annotated datasets were created. A custom CNN model and a transfer learning model utilizing a CNN pre-trained on the collected photo datasets were designed and subsequently analyzed. As a result of the study, the Xception transfer learning model, which demonstrated the best performance, was selected as the urban park user activity image classification model and evaluated through several evaluation indicators. This study is meaningful in that it has built AI as an index that can evaluate the characteristics of urban parks by using user-shared photos on social media. The classification model using Deep Learning mitigates the limitations of manual classification, and it can efficiently classify large amounts of urban park photos. So, it can be said to be a useful method that can be used for the monitoring and management of city parks in the future.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.63-70
• /
• 2022

Although 2D Object detection has been largely improved in the past years with the advance of deep learning methods and the use of large labeled image datasets, 3D object detection from 2D imagery is a challenging problem in a variety of applications such as robotics, due to the lack of data and diversity of appearances and shapes of objects within a category. Google has just announced the launch of Objectron that has a novel data pipeline using mobile augmented reality session data. However, it also is corresponding to 2D-driven 3D object detection technique. This study explores more mature 2D object detection method, and applies its 2D projection to Objectron 3D lifting system. Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a stochastic representation of object regions using Gaussian distributions. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a stochastic Intersection-over-Union. Our experimental results show that the proposed Gaussian representations are closer to annotated segmentation masks in available datasets. Thus, less accuracy problem that is one of several limitations of Objectron can be relaxed.

• (The)Study of the Eastern Classic
• /
• no.68
• /
• pp.539-570
• /
• 2017

This article is for considering and looking through the meaning of Classic of Poetry(Shi jing) Hiku-ka of Kobayashi Issa before reviewing and adapting Classic of Poetry(Shi jing) in Eastern Asia. Issa wrote his works by using Hyanghwa-Gucheop in 1803, and he had adopted it as his creative works of Hikai absorbing Classic of Poetry(Shi jing) for about half a year. There has been no national study about this so far, and this study covered the aspects of Issa's adapting way of Classic of Poetry(Shi jing) in Japan and China. There have been several problems that the contents were limited to Guo-feng and there were no agreement of terminology as well among researchers. To overcome these limitations, therefore, this article aimed at all the works, rejected the view point as just a translation, and denominated this study as Haiku-ka. Above all, this study looked though Issa's Classic of Poetry(Shi jing) by splitting the aspects of Haiku-ka into borrowing topics and materials. In borrowing topics, the works with the topics of homesick and nostalgic parents stood out. Furthermore, annotations and understandings of Issa's original works were deeply involved. In borrowing materials, the original meanings in the works were transformed and changed or even reinterpreted by their own way. Eliminating sublime emotions, furious tone, and condemnation was main characteristic of Haiku-ka in Classic of Poetry(Shi jing). Besides, there were ways of exclusion of reasoning, deviating from the viewpoint of Sigyo(edification by poetry), not including moral senses. In other words, Issa used habits and impressions like the way of Haiku when he was doing Haiku-ka in Classic of Poetry(Shi jing). The meaning that Issa's Hiku-ka of Classic of Poetry(Shi jing) stood out compared to adaptation of Classic of Poetry(Shi jing) in Eastern Asia. Although Classic of Poetry(Shi jing) in Vietnam was transferred in the form of the poem in Vernacular, the meaning and contents were not changed. Moreover, the original works and characters in Joseon were not destroyed because Classic of Poetry(Shi jing) was not liberally translated but literally. However, Issa transferred the Classic of Poetry(Shi jing) in the form of the poem in Vernacular to reveal the value of popular ballads. This was a different adapting way of Classic of Poetry(Shi jing) from that in Eastern Asia.

• Korean Journal of Heritage: History & Science
• /
• v.56 no.1
• /
• pp.22-43
• /
• 2023

This paper deals with the stone standing Avalokitesvara statue in Jeonghyesa Temple that was created by Mangong in 1924. The stone standing Avalokitesvara statue of Jeonghyesa Temple is the earliest extant Buddha statue produced by Mangong, and symbolism was given to Jeonghyesa in the process of its reconstruction. So far, there has been no study that has approached ideas and beliefs through Buddhist studies led by Mangong and specific relics. In order to proceed with this study, Mangong's legal words and anecdotes and newspaper articles during the Japanese colonial era were used to trace the dynamics of Jeonghyesa and Sudeoksa during Mangong's reign, and to investigate the effects obtained from the creation of the large Bodhisattva statue and the meaning of its location. In addition, an interview was attempted with the descendants of master, who were in charge of the sculpture at the time, to confirm the exact construction period and the list of craftsmen. It is judged that the stone standing Bodhisattva statue of Gwanchoksa Temple has been influenced by the double covering and square crown seen in the standing stone statue of Avalokitesvara Bodhisattva of Jeonghyesa Temple, the large hands compared to the body, the proportion between the head and the body, and the sense of enormity felt in the body like a stone pillar. Therefore, we looked at how the standing stone Bodhisattva statue of Gwanchoksa Temple, which was produced in the early Goryeo Dynasty, could have influenced the creation of the Bodhisattva statue in the modern period. A multilateral analysis was attempted on how the image of the Gwanchoksa Bodhisattva statue, which was used as a symbol representing Chungcheongnam-do in the Chosun Exposition held in 1929 and the visit to Gwanchoksa Temple, which began with the laying of the railroad during the Japanese colonial period, was used from the viewpoint of the succession and transformation of the style. With this study as an opportunity, it is hoped that the understanding of the prehistoric Mangong representing the modern period and the horizon of Korean Buddhist sculpture research in the modern period will be broadened.