• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.13-16
• /
• 2016

본 논문에서는 순환 신경망을 이용하여 동영상에서의 배경과 전경을 구분하는 알고리즘을 제안한다. 순환 신경망은 일련의 순차적인 입력에 대해서 내부의 루프(loop)를 통해 이전 입력에 의한 정보를 지속할 수 있도록 구성되는 신경망을 말한다. 순환 신경망의 여러 구조들 가운데, 우리는 장기적인 관계에도 반응할 수 있도록 장단기 기억 신경망(Long short-term memory networks, LSTM)을 사용했다. 그리고 동영상에서의 시간적인 연결 뿐 아니라 공간적인 연관성도 배경과 전경을 판단하는 것에 영향을 미치기 때문에, 공간적 순환 신경망을 적용하여 내부 신경망(hidden layer)들의 정보가 공간적으로 전달될 수 있도록 신경망을 구성하였다. 제안하는 알고리즘은 기본적인 배경차분 동영상에 대해 기존 알고리즘들과 비교할만한 결과를 보인다.

• Journal of the Korean Geographical Society
• /
• v.34 no.3
• /
• pp.265-279
• /
• 1999

경제활동의 세계화는 세계적 금융체계의 출현을 수반하고 있으며 금융부문의 역할은 현대 경제체계에서 중요성을 더하고 있다. 또한 정보통신기술의 발달과 금융기법의 혁신, 자본이동의 자유화는 새로운 조절양식과 이에 따른 조절공간의 변화를 수반한다. 한국의 경우 금융구조조정은 전세계적인 금융위기와 필요에 의한 대응으로 이해되며 제도적 변화와 함께 금융기관의 흡수.합병.퇴출을 통하여 기업부문, 정부부문뿐 아니라 공간적으로도 막대한 영향을 미친다. 일반은행 점포수의 변화를 금융구조조정 이전인 1997년과 이후인 1998년을 비교 분석한 결과 점포수의 급격한 감소와 함께 지역적인 특색이 나타났다. 금융구조조정은 서울.경기를 포함한 수도권에서 가장 활발히 일어나고 있으며, 도시 인구규모에 민감하게 반응하여 소규모 도시일수록 변화의 폭이 감소하고 있다. 구조조정 기간 중에 은행수의 변화는 인구규모와 밀접한 연관성을 나타내고 있다.

• Journal of Korea Game Society
• /
• v.10 no.6
• /
• pp.89-96
• /
• 2010

To identify characteristics of social network farm game based on smart phone platform, this study analyzed how social network play experience connects with the space of farm game. The play experience of social network farm game based on smart phone platform is mainly composed of three modules for cultivating, placing environment, extending space. This study categorized space for external perspective space, internal perspective space, symbolic design space according to space experience theory and researched play experience in these spaces. In farm game players perceive space by fixed point of view, and make their own space a standard unit for reinterpreting and rearranging modules. In this process the space played subjective role not only background to bring co-work play is essential in social network game.

• Journal of Korea Multimedia Society
• /
• v.14 no.11
• /
• pp.1491-1499
• /
• 2011

Now a days, to make good use of tags is a general tendency when users need to upload or search some multimedia data such as images and videos on the Web. In this paper, we introduce an approach to calculate semantic importance of tags and to make re-ranking with them on tagged Web image retrieval. Generally, most photo images stored on the Web have lots of tags added with user's subjective judgements not by the importance of them. So they become the cause of precision rate decrease with simple matching of tags to a given query. Therefore, if we can select semantically important tags and employ them on the image search, the retrieval result would be enhanced. In this paper, we propose a method to make image retrieval re-ranking with the key tags which share more semantic information with a query or other tags based on Wikipedia-based semantic relatedness. With the semantic relatedness calculated by using huge on-line encyclopedia, Wikipedia, we found the superiority of our method in precision and recall rate as experimental results.

• Journal of Internet Computing and Services
• /
• v.9 no.6
• /
• pp.141-153
• /
• 2008

E-learning is a new paradigm of education using Internet media. E-learning is rapidly expanding, since it is not restricted by time and space. However, due to the lack of standardization in e-learning, learning contents are developed redundantly. SCORM has been proposed to address this standardization problems. The mere learning contents are shared, the higher the reusability of contents becomes. Therefore, it is needed to develop methods or tools to help educators or content producers to create a learning course easily. In this paper, we propose an association method that could help educators or content producers to efficiently generate learning courses for a subject. The association method, a learning course generation method suggested by this paper, makes use of existing learning courses and learning contents to create new learning courses suitable to a subject. The association method analyzes statistical information of leaning objects derived from existing learning courses and measures coherence between learning objects to create a learning course. The association method suggested by this paper not only supports educators or content producers for easy generation of learning course but also offers a guideline for developing learning courses.

• Journal of Korean Society for Geospatial Information Science
• /
• v.17 no.2
• /
• pp.3-9
• /
• 2009

These days, the value of the limited land rises in the city according to the increase of the population and the industrial development. And various studies on estimating the land price have been accomplished for the purpose of using the land efficiently. As a result, the officially assessed land price system was arranged. However the system is insufficient to reflect realities. Therefore, in this study, we examined the spatial distribution of the land price by joining spatially the officially assessed land price of Haeundae-gu, Busan from 2004 to 2008 to the map of lot number. We also computed and compared the change rate of the land price for 5 years. And we analyzed the relation between factors including the distance from the subway station, the land use and the land category which have an effect on the officially assessed land price and it using GIS technology.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.167-177
• /
• 2021

Facilities located in the underground space are closely related to the sanitation and safety of the city, and the underground spatial information is precisely constructed and used as important information for facility maintenance, safety, and underground space development. In this study, a method was studied to increase the field usability by increasing the reliability of underground spatial information constructed in Korea and used in the field. For this study, the current status of the construction of underground spatial information in Korea was summarized, and cases of the underground spatial information quality grading system applied in the US, UK, Canada, France, and Australia, which are advanced geospatial information countries, were investigated. In terms of field usability, a questionnaire was conducted on the systems, standards, and management methods related to underground spatial information of field experts and consumers working in related fields in Korea, and statistical analysis was conducted to analyze the relevance of the introduction. Through this study, it was concluded that it is necessary to introduce a quality grading system according to the construction method of underground spatial information, accuracy and reliability, and to improve related systems and regulations.

• Culinary science and hospitality research
• /
• v.16 no.5
• /
• pp.103-117
• /
• 2010

This study investigated emotional-utilitarian motivation to visit a coffee shop and segmented the market based on motivational factors realizing that coffee is considered as emotional and utilitarian goods in reality. As a result of market segmentation, three groups were identified: emotional consumers, utilitarian consumers, and passive consumers. Choice attributes of visiting a coffee shop according to each group were found to be significantly different. Firstly, emotional consumers highly perceived the importance of the emotional factors such as 'coffee taste and mood', 'special coffee', 'clean space' and also the utilitarian factors such 'price benefit', 'internet access,' etc. Therefore, emotional consumers could be utilitarian one at the same time. On the other hand, utilitarian consumers were highly aware of the importance of 'independent space available for a group meeting', 'degrees of being crowded', and 'facilities such as a bathroom and smoking area.' As for the demographic and the behavioral factors of having coffee, only gender, types of coffee, time and places have a significant relation.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.366-374
• /
• 2017

Since a display device such as TV or digital signage is getting larger, the types of media is getting changed into wider view one such as UHD, panoramic and jigsaw-like media. Especially, panoramic and jigsaw-like media is realized by stitching video clips, which are captured by different camera or devices. However, a stitching process takes long time, and has difficulties in applying for a real-time process. Thus, this paper suggests to find out 2D Adjacency Matrix, which tells spatial relationships among those video clips in order to decrease a stitching processing time. Using the Discrete Cosine Transform (DCT), we convert the each frame of video source from the spatial domain (2D) into frequency domain. Based on the aforementioned features, 2D Adjacency Matrix of images could be found that we can efficiently make the spatial map of the images by using DCT. This paper proposes a new method of generating 2D adjacency matrix by using DCT for producing a panoramic and jigsaw-like media through various individual video clips.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.7 no.2
• /
• pp.87-96
• /
• 2004

When watershed spatial database is constructed from DEM, hydrological geographic characteristics of watershed can be easily extracted. And the characteristics can be assigned and managed as the attribute of spatial database. In this study the scheme of constructing framework spatial database which is basic information for managing watershed information is examined. We established framework spatial data and defined the relationship of the data. And framework spatial database of test site was constructed. In this study, HyGIS(Hydrological Geographic Information System) which is developed by domestic technology for making hydrological spatial data and developing water resources system is used. Hydrological geographic characteristics and spatial data is extracted by HyGIS. And the data from HyGIS is used for constructing framework spatial database of test site. Finally, this study suggests the strategy of constructing framework spatial database for developing watershed management system based on river network.