• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.228-239
• /
• 2022

In this paper, we propose an unmanned vehicle scratch detection deep learning model for car sharing services. Conventional scratch detection models consist of two steps: 1) a deep learning module for scratch detection of images before and after rental, 2) a manual matching process for finding newly generated scratches. In order to build a fully automatic scratch detection model, we propose a one-step unmanned scratch detection deep learning model. The proposed model is implemented by applying transfer learning and fine-tuning to the deep learning model that detects changes in satellite images. In the proposed car sharing service, specular reflection greatly affects the scratch detection performance since the brightness of the gloss-treated automobile surface is anisotropic and a non-expert user takes a picture with a general camera. In order to reduce detection errors caused by specular reflected light, we propose a preprocessing process for removing specular reflection components. For data taken by mobile phone cameras, the proposed system can provide high matching performance subjectively and objectively. The scores for change detection metrics such as precision, recall, F1, and kappa are 67.90%, 74.56%, 71.08%, and 70.18%, respectively.

• Journal of Korean Home Economics Education Association
• /
• v.33 no.2
• /
• pp.115-133
• /
• 2021

The purpose of this study is to develop a teaching-learning plans for middle school Home Economics that practices clothing life in response to climate change. Four steps of analysis, design, development, and evaluation were used for the research. 'Phenomenon and cause, impact (environmental, economic and social) and response (relaxation and adaptation)' were selected as educational content elements for climate change through reviewing the literature related to climate change. Six types of middle school Technology and Home Economics textbooks under the 2015 revised curriculum were analyzed using the selected content elements for climate change as the basis for analysis according to the data type(reading data, picture data, activity data) and clothing use cycle (production, purchase, use, and disposal). Based on the content elements of climate change in the clothing life area extracted through textbook analysis, a total of 12 teaching-learning plans in response to climate change were developed by utilizing various teaching and learning methods, data and media. The teaching-learning plans were designed based on an integrated understanding of the phenomena, causes, effects, and responses of climate change for the students to realize the seriousness of climate change and to exercise positive influence on families and society.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.293-301
• /
• 2023

Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.7
• /
• pp.4498-4510
• /
• 2015

The purpose of this study is to investigate effective teaching media for infants' teaching-learning process by comparing the effects of multimedia fairytale activities and picture fairytale listening activities on infants' prosocial actions. Following the purpose of this study, we studied any effect to infants' prosocial actions from multimedia fairytale activities by dividing in two groups. This study was conducted with 5-year-old infants (total 40; 20 experimental group & 20 comparison group) in D daycare center in Daejeon. Verifying data tool were time series corresponding t-test, independent t-test and multi-variant analyses. As a result, multimedia fairytale listening activities are more effective for infants' prosocial actions. It has meaningful difference in the interpersonal relationship skills and early childhood education adapt which is sub-area of infant's prosocial actions. So, for various and high-quality early childhood education, using multimedia teaching media is more effective than existing teaching media.

• Journal of Korea Game Society
• /
• v.18 no.2
• /
• pp.109-120
• /
• 2018

Gamification is an important technology for the museum experience in the future, but there is a lack in both its application and academic studies in Korea. Therefore this study targets the technical strategies of museum gamification by studying domestic and international cases. For this purpose, this study analyzes and compares the cases as personalization, and audience interaction of museum experience and sees how the structure of the digital program affects the museum experience in detail by applying MDA framework to the comparisons. For visitors' active interaction with the museums, gamification should be designed in a way to contribute to visual expression of self identity, utilization of the museum space, constructivist learning free from limit on space and time, and interaction with other people.

• Journal of Korea Multimedia Society
• /
• v.4 no.4
• /
• pp.297-305
• /
• 2001

Recently advances in high-speed networks and multimedia computer technologies allow new types of multimedia applications to manipulate large volumes of multimedia data. However, in the real time and/or the heterogeneous data transmissions, there are many difficulties such as network transmission delay, the implementation difficulties, and so on. To solve these problems, in this paper, we extend the method of the multimedia service design which is proposed by OMG. To do this, we suggest an efficient real time audio/video stream framework, called Smart Explorer, based un CORBA and JMF Java Media API. And we separate the transmission path of control data from that of media data and use RTP/RTCP protocol for efficient real time audio/video transmission. Also we show the appropriate implementation of the audio/video stream system based on our suggested framework Smart Explorer. In the future, we expect our audio/video stream system to be applied to the real time communication software such as broadcasting, distance learning, and video conferencing.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.05a
• /
• pp.251-254
• /
• 2006

The application of reflex media in education has been widely used in the aspects of teaching & learning method, humanitarian education and the culture of school lives. It has been resulted from the generality of the applicable scope within conveying the information, propagation velocity, and the efficiency of the amount of conveyable information through the reflex. To utilize this kind of efficiency of reflex media in producing new graduation culture, I intend to show students the graduate reflex including their 3years' school lives and try to find out its effect from them. And then with this result I have studied the changes of the students behavior in the graduation ceremony. As a result I can notice that the intent of graduation reflex which aims to look back into their past and keep in mind it has been reflected to students. In addition I can ascertain their friendship and love for their school have been lifted while watching the reflex with laugh and cry.

• Journal of Korea Multimedia Society
• /
• v.4 no.5
• /
• pp.446-454
• /
• 2001

A long-distance education method using the computational environment has been developed and implemented for quite some time. However, there has been some difficulty in the simulation of face-to-face instruction due to limitations in performance of the computers and the networks. Continued development of multimedia technologies has now made it possible to simulate face-to-face instruction, recording the teachers' instructions in the form of a screen dump. In this paper, we propose a system that allows the teacher to make loaming materials available on the Web using Window Media Technology(WMT). This technology also allows remote site users to view the contents at their convenience. A media encoder acquires the lessons and stores them as moving pictures. The lessons are displayed on the screen as the teacher explains them. The learning materials are stored in a Windows media file format, the file is stored on a lecture server and provided to the user using a streaming method in real time. The users can view the contents on the Web without requiring a special player. The proposed system consists of a lecture writer module, a lecture server module and a lecture client module.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.776-788
• /
• 2020

In this paper, a vehicle type recognition system using deep learning and a license plate recognition system are proposed. In the existing system, the number plate area extraction through image processing and the character recognition method using DNN were used. These systems have the problem of declining recognition rates as the environment changes. Therefore, the proposed system used the one-stage object detection method YOLO v3, focusing on real-time detection and decreasing accuracy due to environmental changes, enabling real-time vehicle type and license plate character recognition with one RGB camera. Training data consists of actual data for vehicle type recognition and license plate area detection, and synthetic data for license plate character recognition. The accuracy of each module was 96.39% for detection of car model, 99.94% for detection of license plates, and 79.06% for recognition of license plates. In addition, accuracy was measured using YOLO v3 tiny, a lightweight network of YOLO v3.

• The Journal of the Korea Contents Association
• /
• v.8 no.11
• /
• pp.162-170
• /
• 2008

The promotion of new product is one of most important object for exhibition design. The majority of conventional exhibition technique has been implemented through one-way communication. However, using digital technology, development of new exhibition techniques is necessary for promotion of high-tech products and consideration of the phases of the times. This paper propose the various possibilities of exhibition design model which is using camera sensing and video input/output. Interactivity is efficient method to communicate between viewers and displays. Viewers can be participate actively and exhibition goal will be accomplish through this. Using camera as visual senses, video input/output technique is offered not only introducing new product but also entertaining viewers through various ways of representation. Physical experience and learning process can be expected from the exhibition space and the object. The classification of the artist who are using video input/output technique and exhibition examples are described. The collaboration on a work with the new media artist and the exhibition design will be complement each other. It will be solved the problems of realization and corporation of idea and technology.