• 한국멀티미디어학회논문지
• /
• 제23권7호
• /
• pp.803-811
• /
• 2020

This paper proposes an image classification algorithm that transforms the number of convolution layers in the residual block of ResNet, CNN's representative method. The proposed method modified the structure of 34/50 layer of ResNet structure. First, we analyzed the performance of small and many convolution layers for the structure consisting of only shortcut and 3 × 3 convolution layers for 34 and 50 layers. And then the performance was analyzed in the case of small and many cases of convolutional layers for the bottleneck structure of 50 layers. By applying the results, the best classification method in the residual block was applied to construct a 34-layer simple structure and a 50-layer bottleneck image classification model. To evaluate the performance of the proposed image classification model, the results were analyzed by applying to the cifar10 dataset. The proposed 34-layer simple structure and 50-layer bottleneck showed improved performance over the ResNet-110 and Densnet-40 models.

• 기술경영경제학회:학술대회논문집
• /
• 기술경영경제학회 2006년도 제28회 동계학술발표회 논문집
• /
• pp.78-102
• /
• 2006

Networks, services and industries have been converging with the advent of digital convergence by technology advancements of digitalization, broadband and interactivity in the areas of information-communication and broadcasting technologies. Especially, this convergence of technology and market has been blurring the boundary of telecommunication and broadcasting sectors, and the severe competition seems to be inevitable due to the lack of the differentiation in broadcasting media and contents. In this study, we regard the competition phenomenon in the digital convergence between telecommunication and broadcasting as the platform competition in two-sided markets which have been actively studied since 2000, and analyzed it using modified Hotelling's location model. According to the analysis of platform competition on the effects of the differentiation of platform (t) , killer component $(\mu)$ and component compatibility $(\theta)$ , it is shown that two differentiated platforms are simultaneously used in case of the decrease of substitution effects, and the profit of platform with killer contents is increased, but the profit of platforms with higher compatibility is decreased. The policy implication is that it is especially necessary to modify the policy and regulation on media contents considering the growing competition in media. On the other hand, differentiated and reasonable policy is required to make fair competition and active market environment.

• 한국지능시스템학회논문지
• /
• 제23권6호
• /
• pp.500-504
• /
• 2013

본 논문은 웹 브라우저 기반 통신 방식인 WebRTC를 이용하여 고사양 저가의 단말인 Set Top Box(STB)에서 인터렉션을 할 수 있는 다국어l 화상 안내 응용 서비스 개발에 관한 것이다. 서버는 원격으로 연결된 씬 클라이언트의 디지털 정보 디스플레이와 함께 웹 카메라에 액세스하고 사용자와 안내 정보를 교환한다. 또한, 서버는 고화질 비디오 압축의 가상화 전송 방식을 사용함으로써 STB의 성능에 종속되지 않고 thin client STB에서 재생되는 원격 영상 안내 서비스 시스템을 제안한다.

• 한국융합학회논문지
• /
• 제7권2호
• /
• pp.13-17
• /
• 2016

컴퓨터 및 인터넷(온라인) 서비스 보급은 약 10여년이라는 시간을 통해 급속도로 발전 및 진화하고 있다. 또한 인간 생활의 많은 부분에 시간과 비용을 절감하는 효과를 가져왔다. 그러나 하나의 정보가 다각화 되면서 적용 범위 및 표현범위가 많이 세분화되고 있는 실정이다. 특히 이러한 세분화 된 정보를 각 분야별로 통합 할 수 있을지는 모르나, 사용자가 시각적으로 한번에 인식하기에는 다소 어렵다. 따라서, 본 논문은 최근 인터넷 및 프로그램의 UI가 매우 중요시 됨에 따라, 기존 GUI에서 통일화된 디자인으로 프로그램들이 다각적으로 개발이 이루어짐으로써, 이를 개선하고 분석하여, 사용자 중심의 UI디자인의 중요성에 대해서 제안하고자 한다.

• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.98-102
• /
• 2023

This paper presents a study on how augmenting semi-synthetic image data improves the performance of human detection algorithms. In the field of object detection, securing a high-quality data set plays the most important role in training deep learning algorithms. Recently, the acquisition of real image data has become time consuming and expensive; therefore, research using synthesized data has been conducted. Synthetic data haves the advantage of being able to generate a vast amount of data and accurately label it. However, the utility of synthetic data in human detection has not yet been demonstrated. Therefore, we use You Only Look Once (YOLO), the object detection algorithm most commonly used, to experimentally analyze the effect of synthetic data augmentation on human detection performance. As a result of training YOLO using the Penn-Fudan dataset, it was shown that the YOLO network model trained on a dataset augmented with synthetic data provided high-performance results in terms of the Precision-Recall Curve and F1-Confidence Curve.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2016년도 추계학술대회
• /
• pp.72-75
• /
• 2016

본 논문에서는 고정된 카메라 환경에서 카메라의 흔들림에 강인한 배경 영상을 생성할 수 있는 배경 모델링 방법을 제안한다. 흔들리지 않은 영상을 기준 영상으로 설정하고 기준 영상에서 해리스 코너 검출기를 이용하여 특징점들을 검출한다. 이후 입력 영상에 대해 동일한 방식으로 특징점을 추출한 뒤 탬플릿 매칭과 거리 비교를 이용하여 공통적으로 나타나는 배경 영역들에 대한 특징점만을 선별한다. 기준 영상에서의 특징점과 목표 영상에서의 대응되는 특징점 쌍을 이용하여 보정을 위한 호모그래피 행렬을 계산한다. 이렇게 계산된 보정 행렬을 이용하여 흔들린 목표 영상을 보정하게 된다. 흔들린 영상들을 보정한 후 보정된 영상들로 배경 모델을 생성하게 되면 정확한 배경 모델을 생성할 수 있다.

• International Journal of Advanced Culture Technology
• /
• 제11권3호
• /
• pp.332-337
• /
• 2023

The purpose of the study was to analyze consumers' perceptions of gamification. Based on the analyzed data, we would like to provide data by systematically organizing the concept, game elements, and mechanisms of gamification. Recently, gamification can be easily found around medical care, corporate marketing, and education. This study collected keywords from social media portal sites Naver, Daum, and Google from 2018 to 2023 using TEXTOM, a social media analysis tool. In this study, data were analyzed using text mining, semantic network analysis, and CONCOR analysis methods. Based on the collected data, we looked at the relevance and clusters related to gamification. The clusters were divided into a total of four clusters: 'Awareness of Gamification', 'Gamification Program', 'Future Technology of Gamification', and 'Use of Gamification'. Through social media analysis, we want to investigate and identify consumers' perceptions of gamification use, and check market and consumer perceptions to make up for the shortcomings. Through this, we intend to develop a plan to utilize gamification.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 하계학술대회
• /
• pp.601-604
• /
• 2020

방송예술 및 콘텐츠 제작 역량을 교육시키는 방송예술특성화 대학으로서 C3(Creativity, Convergence, Contents) 방송예술 창의융합교육 모델인 융합수업을 개설하고 전체 학과에서 신청한 학생들을 대상으로 교육을 진행하였다. 융합수업은 전공이 다른 학생들이 희망하는 콘텐츠 제작과정을 수강하고, 방송사와 산업체에서 실무경험이 풍부한 교수와 전문가들이 직접 콘텐츠 제작을 지도함으로써 고품질의 수준 높은 콘텐츠 제작 교육을 경험할 수 있는 수업이다. 즉, 재학 중 학교수업을 통해 미리 현장 경험을 쌓음으로써 취업 즉시 콘텐츠 제작 역량을 발휘할 수 있는 자신감 함양과 제작현장에 기여할 수 있는 융합형 인재양성 교육프로그램인 것이다. 본 연구에서는 대학이 보유하고 있는 방송용 버츄얼 스튜디오를 활용한 가상 세트 영상 제작 교육 『영화담』을 제작하는 융합수업과 드론 항공촬영을 활용한 제작교육 『드론 탐사대』 융합수업을 실시하여 첨단 기술을 활용한 콘텐츠 협업 제작의 효과와 학생들의 만족도를 분석하였다.

• Journal of Information Display
• /
• 제3권2호
• /
• pp.19-25
• /
• 2002

In this paper, a new target extraction algorithm is proposed, in which the coordinates of target are obtained adaptively by using the difference image information and the optical BPEJTC(binary phase extraction joint transform correlator) with which the target object can be segmented from the input image and background noises are removed in the stereo vision system. First, the proposed algorithm extracts the target object by removing the background noises through the difference image information of the sequential left images and then controlls the pan/tilt and convergence angle of the stereo camera by using the coordinates of the target position obtained from the optical BPEJTC between the extracted target image and the input image. From some experimental results, it is found that the proposed algorithm can extract the target object from the input image with background noises and then, effectively track the target object in real time. Finally, a possibility of implementation of the adaptive stereo object tracking system by using the proposed algorithm is also suggested.

• Journal of Information Technology Applications and Management
• /
• 제19권4호
• /
• pp.185-196
• /
• 2012

Domestic digital signage industry has been growing in line with the Internet and intelligent devices like smart phones. However, policies for digital signage need to be supplemented because existing policies are only focused on regulations for outdoor advertisements. Moreover, while digital technologies have been developed, there are few contents technologies to support the digital technologies. In this context, this research aims to identify the problems in relation to the domestic digital signage industry and seek for measures to solve the problems. Various case studies and literature review were conducted to identify problems in terms of policy, technology and service, and measures for revitalizing the digital signage industry were suggested. The research is expected to help digital signage to serve as new convergence media available for customization targeting and user participation.