• Journal of Broadcast Engineering
• /
• 제24권1호
• /
• pp.132-141
• /
• 2019

The necessity of transmitting video data over a narrow-bandwidth exists steadily despite that video service over broadband is common. In this paper, we propose a scalable video coding framework for low-resolution video transmission over a very narrow-bandwidth network by super-resolution of decoded frames of a base layer using a convolutional neural network based super resolution technique to improve the coding efficiency by using it as a prediction for the enhancement layer. In contrast to the conventional scalable high efficiency video coding (SHVC) standard, in which upscaling is performed with a fixed filter, we propose a scalable video coding framework that replaces the existing fixed up-scaling filter by using the trained convolutional neural network for super-resolution. For this, we proposed a neural network structure with skip connection and residual learning technique and trained it according to the application scenario of the video coding framework. For the application scenario where a video whose resolution is $352{\times}288$ and frame rate is 8fps is encoded at 110kbps, the quality of the proposed scalable video coding framework is higher than that of the SHVC framework.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 한국방송∙미디어공학회 2020년도 하계학술대회
• /
• pp.732-735
• /
• 2020

기존에 지도학습 방법은 성능은 좋지만, 학습할 때 비디오 데이터와 정답 라벨이 있어야 한다. 그러나 이러한 데이터의 라벨을 수동으로 붙여줘야 하는 문제점과 그에 필요한 시간과 돈이 크다는 것이다. 이러한 문제점을 해결하기 위한 다양한 방법 중 자기지도학습(Self-Supervised Learning) 중 하나인 회전 방법을 비디오 데이터에 적용하여 학습하는 연구를 진행하였다. 본 연구에서는 두가지 방법을 제안한다. 먼저 기존의 비디오 데이터를 입력으로 받으면 단순히 비디오 자체를 회전시키는 것이 아닌 입력으로 들어온 비디오의 각각 프레임이 시간이 지나면서 일정한 속도로 회전을 시킨다. 이때의 회전은 총 네 가지 각도[0, 90, 180, 270]를 분류하도록 하는 방법론이다. 두 번째로 비디오의 프레임이 시간이 지나면서 변할 때 프레임 별로 고정된 각도로 회전시키는데 이때 회전하는 속도 네 가지 [1x, 0.5x, 0.25x, 0.125]를 분류하도록 하는 방법론이다. 이와 같은 제안하는 pretext task들을 통해 네트워크를 학습한 뒤, 학습된 모델을 fine tune 시켜 비디오 분류에 대한 실험을 수행 및 결과를 도출하였다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• 제22권6호
• /
• pp.1293-1300
• /
• 2012

With the rapid evolution of mobile devices and the development of wireless networks, users of mobile social network service on smartphone have been increasing. Also the security of personal information as a result of real-time communication and information-sharing are becoming a serious social issue. In this paper, a framework that can be linked with a social network services platform is designed using OpenAPI. In addition, we propose an authentication and detection mechanism to enhance the level of personal information security. The authentication scheme is based on an user ID and password, while the detection scheme analyzes user-designated input patterns to verify in advance whether personal information protection guidelines are met, enhancing the level of personal information security in a social network service environment. The effectiveness and validity of this study were confirmed through performance evaluations at the end.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2009년도 춘계학술발표대회
• /
• pp.593-596
• /
• 2009

자연언어 데이터베이스 인터페이스 시스템은 입력된 자연언어를 데이터베이스의 질의문(query)으로 바꿔주는 시스템으로, 데이터베이스에 잘 모르는 일반 사용자도 쉽게 데이터베이스를 이용할 수 있게 하는 장점이 있다. 본 논문에서는, 범용적인 분야의 자연언어 데이터베이스 인터페이스 시스템을 설계하기 위한 하나의 틀을 제안한다. 패턴 매칭과 구문 분석 기법을 동시에 사용하여 자연언어 처리 능력과 속도를 향상시켰으며, 패턴을 4개 분류로 나누어 의미 처리를 가능하게 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.1028-1030
• /
• 2020

과거 몇 년간의 데이터를 기반으로 현재 KBO 승패를 예측하고자 하는 것으로, 경기 초반 페이스가 얼마나 승패에 영향을 미치는지 파악하고자 한다. 경기의 이닝별 데이터로 딥러닝·머신러닝을 이용해 승리 팀을 예측하여 리그 순위를 예측하고, Flask 웹 프레임워크를 통해 입력값을 받아 예측해 주는 웹사이트를 구축하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 한국방송∙미디어공학회 2021년도 하계학술대회
• /
• pp.95-96
• /
• 2021

본 논문에서는 단안비디오 입력으로부터 각 SAI(sub-aperture image)간의 넓은 기준선을 갖는 라이트필드 합성기법을 제안한다. 기존의 라이트필드 영상은 취득의 어려움에 의해 규모가 작고 특정 물체위주로 구성되어 있어 컴퓨터 비전 및 그래픽스 분야의 최신 딥러닝 기법들을 라이트필드 분야에 적용하기 어렵다는 문제를 갖고 있다. 이러한 문제점들을 해결하기 위해 사실적 렌더링 기반의 가상환경상에서 실제환경과 유사함을 갖는 데이터를 취득하였다. 생성한 데이터셋을 이용하여 기존의 새로운 시점을 생성하는 기법 중 하나인 다중 평면 영상(Multi Plane Image) 기반 합성기법을 통해 라이트필드 영상을 합성한다. 제안하는 네트워크는 단안비디오의 연속된 두개의 프레임으로부터 MPI 추정하는 네트워크와 입력영상의 깊이 정보를 추정하는 네트워크로 구성되어 있다.

• Journal of Broadcast Engineering
• /
• 제25권4호
• /
• pp.545-559
• /
• 2020

In this paper, we propose a content creation framework that enables users without programming experience to easily create interactive media content that responds to user gestures. In the proposed framework, users define the gestures they use and the media effects that respond to them by numbers, and link them in a text-based configuration file. In the proposed framework, the interactive media content that responds to the user's gesture is linked with the dynamic projection mapping module to track the user's location and project the media effects onto the user. To reduce the processing speed and memory burden of the gesture recognition, the user's movement is expressed as a gray scale motion history image. We designed a convolutional neural network model for gesture recognition using motion history images as input data. The number of network layers and hyperparameters of the convolutional neural network model were determined through experiments that recognize five gestures, and applied to the proposed framework. In the gesture recognition experiment, we obtained a recognition accuracy of 97.96% and a processing speed of 12.04 FPS. In the experiment connected with the three media effects, we confirmed that the intended media effect was appropriately displayed in real-time according to the user's gesture.

• Journal of Broadcast Engineering
• /
• 제24권5호
• /
• pp.755-764
• /
• 2019

Currently commercially available light field cameras are difficult to acquire 5D light field video since it can only acquire the still images or high price of the device. In order to solve these problems, we propose a deep learning based method for synthesizing the light field video from monocular video. To solve the problem of obtaining the light field video training data, we use UnrealCV to acquire synthetic light field data by realistic rendering of 3D graphic scene and use it for training. The proposed deep running framework synthesizes the light field video with each sub-aperture image (SAI) of $9{\times}9$ from the input monocular video. The proposed network consists of a network for predicting the appearance flow from the input image converted to the luminance image, and a network for predicting the optical flow between the adjacent light field video frames obtained from the appearance flow.

• The Journal of the Korea Contents Association
• /
• 제9권12호
• /
• pp.556-565
• /
• 2009

In this paper, we propose a CAD software framework to automatically generate a shop drawing. Shop drawing is to draw the geometric figures representing an arrangement of steel bars for a concrete building on its structural design, based on its construction specifications and the design rules, and its well-formed process lead to be automated. A key point of the design automation is to minimize the user interactions by automatically recognizing the design specifications and to finally generate the shape of the geometric figures. The graphic pipeline of the proposed framework consists of four stages; a specification DB, specification extraction, binding, and rendering. To effectively extract all specifications only for a figure from the DB and bind them to its shape, we use a hierarchical approach; the specifications are classified into three common, structural, and figure classes, and each attribute is extracted in design phases. Based on our framework, we implemented a specialized CAD for shop drawing using AutoCAD and could easily update it according to user's demands.

• Journal of KIISE
• /
• 제42권12호
• /
• pp.1486-1494
• /
• 2015

While Linux-based mobile devices such as smartphones are increasingly used, they often exhibit poor response time. One of the factors that influence the user-perceived interactivity is the high page fault rate of interactive tasks. Pages owned by interactive tasks can be removed from the main memory due to the memory contention between interactive and background tasks. Since this increases the page fault rate of the interactive tasks, their executions tend to suffer from increased delays. This paper proposes a framework-assisted selective page protection mechanism for improving interactivity of Linux-based mobile devices. The framework-assisted selective page protection enables the run-time system to identify interactive tasks at the framework level and to deliver their IDs to the kernel. As a result, the kernel can maintain the pages owned by the identified interactive tasks and avoid the occurrences of page faults. The experimental results demonstrate the selective page protection technique reduces response time up to 11% by reducing the page fault rate by 37%.