• 디지털산업정보학회논문지
• /
• 제8권4호
• /
• pp.83-90
• /
• 2012

With the rapid growth of internet infrastructure, World Wide Web is evolving recently into various services such as cloud computing, social network services. It simply go beyond the sharing of information. It started to provide new services such as E-business, remote control or management, providing virtual services, and recently it is evolving into new services such as cloud computing and social network services. These kinds of communications through World Wide Web have been interested in and have developed user-centric customized services rather than providing provider-centric informations. In these environments, it is very important to check and analyze the user requests to a website. Especially, estimating user preferences is most important. For these reasons, analyzing web logs is being done, however, it has limitations that the most of data to analyze are based on page unit statistics. Therefore, it is not enough to evaluate user preferences only by statistics of specific page. Because recent main contents of web page design are being made of media files such as image files, and of dynamic pages utilizing the techniques of CSS, Div, iFrame etc. In this paper, large log analyzer was designed and executed to analyze web server log to estimate web contents preferences of users. With mapreduce which is based on Hadoop, large logs were analyzed and web contents preferences of media files such as image files, sounds and videos were estimated.

• 대한가정학회지
• /
• 제48권9호
• /
• pp.113-123
• /
• 2010

This study describes the beginning and further development of a collection web-based materials for an efficient approach to culinary practice education. A database was created using a five-step process of analysis, design, development, operation and evaluation. The menu for the web-based culinary practice educational materials included cooking basics, the real status of cooking, cooking related knowledge, performance evaluation, a data room and a bulletin board. As at 30 July, 2010, the datadase of educational materials, contained a total of 571 items. These comprised 139 cooking pictures, 33 recipes, 22 cooking videos, 74 cooking animations, 57 collections of basic knowledge, 14 evaluation reports, 21 supplementary textbooks, and 211 sets of other related information. The webbased materials are adequate for culinary education purposes, and their use is expected to be very highly valued.

• 디지털산업정보학회논문지
• /
• 제19권3호
• /
• pp.1-11
• /
• 2023

Unlike in the past, when the demand for web content was increasing and the use behavior of watching short videos was changed, unlike the past when only TV dramas and differentiation were mentioned, web dramas are more firmly established through various attempts. A typical form change is commerce of web dramas. Recently, more and more cases have been produced in the form of product sales by securing real-time functioned, which are disadvantages of commerce, through web dramas. In this trend, web dramas are also increasing interest in product sales. This can be said to be a form developed from the concept of a company's PPL, and the number of companies that use web dramas that predict continuous growth as strategic product promotion and marketing means is continuously increasing. Therefore, this study provides basic data on consumer behavior to collect product information and purchase products using web dramas to companies that are using or considering web dramas, and through this, companies design and establish marketing strategies using web dramas.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.230-240
• /
• 2022

Sharing of online videos via internet is an emerging and important concept in different types of applications like surveillance and video mobile search in different web related applications. So there is need to manage personalized web video retrieval system necessary to explore relevant videos and it helps to peoples who are searching for efficient video relates to specific big data content. To evaluate this process, attributes/features with reduction of dimensionality are computed from videos to explore discriminative aspects of scene in video based on shape, histogram, and texture, annotation of object, co-ordination, color and contour data. Dimensionality reduction is mainly depends on extraction of feature and selection of feature in multi labeled data retrieval from multimedia related data. Many of the researchers are implemented different techniques/approaches to reduce dimensionality based on visual features of video data. But all the techniques have disadvantages and advantages in reduction of dimensionality with advanced features in video retrieval. In this research, we present a Novel Intent based Dimension Reduction Semi-Supervised Learning Approach (NIDRSLA) that examine the reduction of dimensionality with explore exact and fast video retrieval based on different visual features. For dimensionality reduction, NIDRSLA learns the matrix of projection by increasing the dependence between enlarged data and projected space features. Proposed approach also addressed the aforementioned issue (i.e. Segmentation of video with frame selection using low level features and high level features) with efficient object annotation for video representation. Experiments performed on synthetic data set, it demonstrate the efficiency of proposed approach with traditional state-of-the-art video retrieval methodologies.

• 한국컴퓨터정보학회논문지
• /
• 제27권5호
• /
• pp.37-45
• /
• 2022

2020년 기준 대표적인 온라인 동영상 플랫폼인 유튜브에는 1분에 약 500시간의 동영상이 업로드되고 있다. 이에 업로드된 다수의 다양한 동영상을 통해 정보를 획득하는 사용자의 수가 늘고 있어 온라인 동영상 플랫폼들은 더 나은 추천 서비스를 제공하기 위해 노력하고 있다. 현재 사용되고 있는 추천 서비스는 사용자의 시청 기록을 기반으로 사용자에게 동영상을 추천하는데 이는 교육용 동영상과 같이 특정 목적 및 관심사를 다루는 동영상 추천에 좋은 방법이 아니다. 최근 추천 시스템은 사용자의 시청 기록뿐만 아니라 아이템의 콘텐츠 특징을 함께 활용한다. 본 논문에서는 유튜브를 기반으로 교육용 동영상 추천을 위한 교육용 동영상의 콘텐츠 특징을 추출하고, 이를 활용하는 추천 시스템을 설계하여 웹 애플리케이션으로 구현한다. 사용자들의 만족도를 조사하여 추천 시스템의 추천 성능의 만족도 85.36%, 편의성 만족도 87.80%를 보인다.

• 한국콘텐츠학회논문지
• /
• 제17권11호
• /
• pp.312-318
• /
• 2017

최근 고화질 영상 입력장치가 일반화 되고 있으며, 실시간으로 입력된 영상을 한 곳에서 동시에 볼 수 있는 중앙관제시스템이 필수 요소가 되고 있다. 이때 프로그램을 따로 설치하지 않고, 웹을 통한 접근을 하려는 시도들이 있으나, 여러 개의 고화질 영상을 동시에 웹 브라우저를 통해 시청하려하면, 웹 브라우저가 강제 종료되는 현상이 발생된다. 본 논문에서는 실시간 고화질 영상에 대한 웹기반의 HLS 멀티뷰 시스템을 제안한다. 화면으로 보이는 멀티뷰 화면을 트랜스코딩을 통해서 재구성하였고, 보안의 취약점이 있는 ActiveX를 사용하지 않으면서도, 통시에 웹브라우저를 통해서 여러 영상 입력을 모니터링 할 수 있는 시스템을 구현 하였다.

• 디지털산업정보학회논문지
• /
• 제8권1호
• /
• pp.157-170
• /
• 2012

Recently, user-created video shows high increasing in production and consumption. Among these, videos records an identical subject in limited space with multi-view are coming out. Occurring main reason of this kind of video is popularization of portable camera and mobile web environment. Multi-view has studied in visually representation technique fields for point of view. Definition of multi-view has been expanded and applied to various contents authoring lately. To make user-created videos into multi-view contents can be a kind of suggestion as a user experience for new form of video consumption. In this paper, we show the possibility to make user-created videos into multi-view video content through analyzing multi-view video contents even there exist attribute differentiations. To understanding definition and attribution of multi-view classified and analyzed existing multi-view contents. To solve time axis arranging problem occurred in multi-view processing proposed audio matching method. Audio matching method organize feature extracting and comparing. To extract features is proposed MFCC that is most universally used. Comparing is proposed n by n. We proposed multi-view video contents that can consume arranged user-created video by user selection.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제7권6호
• /
• pp.582-592
• /
• 2001

대용량 영상을 다루는 디지털 비디오 라이브러리나 웹 방송에서는 영상 색인이 매우 중요한 역할을 하며, 이는 영상을 내용 단위로 분할하는 알고리즘에 기반한다. 본 논문에서 구현된 V2Web Studio는 영상 색인을 지원하는 시스템으로서, 샷 경계 검출 알고리즘을 이용한 영상 클립 생성 시스템이다. V2Web Studio는 영상 클립 생성 과정을 1) 영상 신호를 분석하여 샷 경계를 자동 검출하는 단계, 2) 검출된 결과에 포함될 수 있는 오류를 수작업으로 제거하는 단계, 3) 물리적인 샷 경계를 논리적인 계층구조로 모델링하는 단계, 4) 계층구조로 모델링된 각 모델링 인스턴스를 다양한 표준 압축 포맷으로 생성하는 단계로 구분하고, 각 단계에 해당하는 작업은 샷 검출기, 샷 검증기, 영상 모델기, 클립 생성기라는 독립적인 소프트웨어 도구로 구현하였다.

• 한국컴퓨터정보학회논문지
• /
• 제24권3호
• /
• pp.87-93
• /
• 2019

In this paper, we propose a real-time drone-based violent protest detection system. Our proposed system uses drones to detect scenes of violent protest in real-time. The important problem is that the victims and violent actions have to be manually searched in videos when the evidence has been collected. Firstly, we focused to solve the limitations of existing collecting evidence devices by using drone to collect evidence live and upload in AWS(Amazon Web Service)[1]. Secondly, we built a Deep Learning based violence detection model from the videos using Yolov3 Feature Pyramid Network for human activity recognition, in order to detect three types of violent action. The built model classifies people with possession of gun, swinging pipe, and violent activity with the accuracy of 92, 91 and 80.5% respectively. This system is expected to significantly save time and human resource of the existing collecting evidence.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.95-97
• /
• 2019

본 논문에서는 비디오 데이터를 이용한 감독 학습 프레임 워크를 제안한다. 최근 Deep Convolutional Neural Networks의 성공으로 많은 분야에서 사용되고 있다. DCNNs 모델 성능의 중요한 요소 중 하나는 Large-cale Dataset을 구축하는 것으로 Small-scale Dataset으로 모델을 학습한다면 과적합 및 일반화 오류를 해결하기 어렵다. 이러한 문제점을 해결하는 방법으로 이미지 왜곡을 통한 데이터 셋을 증가 또는 Dropout 기법 등을 사용하였지만 원본 데이터가 적은 경우에는 모델이 일반화 능력을 갖기 어렵다. 따라서 본 논문에서는 이러한 문제점을 보완하고자 Web으로부터 얻은 비디오에서 해당 Class와 관련된 프레임들을 추출하여 보다 쉽게 데이터 셋을 확장하고, 모델의 성능을 향상 시키는 방법을 제안한다.