• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권4호
• /
• pp.153-160
• /
• 2021

IT 기술 발달에 따른 영상 콘텐츠 생산과 소비가 증가함에 따라 영상 콘텐츠를 통한 제품 리뷰 정보로 구매의사 결정이 빈번해졌다. 따라서, 리뷰 영상에 대한 신뢰성을 평가할 필요가 있다. 본 연구에서는 제품 리뷰 영상을 얼굴 표정 분석과 텍스트 마이닝을 통해 리뷰어의 표정과 음성을 분석하여 영상의 신뢰도를 분석한다. 영상 내 인물 표정의 감성 값을 추출하는 알고리즘을 활용하여 비언어 감성을 정량화하고, 유의미한 감정 변화 구간을 추출한다. 유의미한 감정 변화 구간의 리뷰어 음성을 텍스트화하여 표준어 및 비표준어 감성 사전 활용을 통해 긍정과 부정으로 리뷰에 대한 언어 감성 분석 후 수치화 한다. 비언어 감성 분석과 언어 감성 분석의 결과를 통합하여 일치 여부에 따라 신뢰도를 도출한다. 본 연구를 통해 영상 콘텐츠의 신뢰성 평가 방법을 제시한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.591-596
• /
• 1999

In this paper, we present a joint quality control system to be able to accurately control the relative picture quality among the video programs in terms of PSNR. The joint quality control system allows variable bit rate (VBR) for each video program to maintain the pre-determined relative picture quality among the aggregated video programs while keeping a constant sum of the bit rates for all programs to be transmitted over a single constant bit rate (CBR) channel. This is achieved by simultaneous controlling the video encoders to generate VBR video streams at the central controller. Furthermore we also suggest buffer regulation method based on the analysis of the constraints imposed by sender/receiver buffer sizes and total transmission rate. Through various simulation results, it is found that our quality control systems guarantee that the video buffers do not overflow and underflow and the quality control errors do not exceed 0.1 ㏈.

• Journal of Multimedia Information System
• /
• 제4권2호
• /
• pp.73-78
• /
• 2017

The Future Video Coding (FVC) is a new state of the art video compression standard that is going to standardize, as the next generation of High Efficiency Video Coding (HEVC) standard. The FVC standard applies newly designed block structure, which is called quadtree plus binary tree (QTBT) to improve the coding efficiency. Also, intra and inter prediction parts were changed to improve the coding performance when comparing to the previous coding standard such as HEVC and H.264/AVC. Experimental results shows that we are able to achieve the average BD-rate reduction of 25.46%, 38.00% and 35.78% for Y, U and V, respectively. In terms of complexity, the FVC takes about 14 times longer than the consumed time of HEVC encoder.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2011년도 춘계학술논문집 1부
• /
• pp.371-374
• /
• 2011

Recently, retrieval of various video data has become an important issue as more and more multimedia content services are being provided. To effectively deal with video data, a semantic-based retrieval scheme that allows for processing diverse user queries and saving them on the database is required. In this regard, this paper proposes a semantic-based video retrieval system that allows the user to search diverse meanings of video data for electrical safety-related educational purposes by means of automatic annotation processing. If the user inputs a keyword to search video data for electrical safety-related educational purposes, the mobile agent of the proposed system extracts the features of the video data that are afterwards learned in a continuous manner, and detailed information on electrical safety education is saved on the database. The proposed system is designed to enhance video data retrieval efficiency for electrical safety-related educational purposes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• International Journal of Contents
• /
• 제18권1호
• /
• pp.27-39
• /
• 2022

Short videos are becoming more popular in mobile Internet age. Not only people's media consumption patterns have been changed by the rise of this new media form, but also it has posed challenges to public psychological well-being. For many netizens, their entertainment needs have been met by watching short videos. However, many side effects, such as addiction and anxiety, reduce users' subjective well-being instead of satisfying the entertainment motivation after watching short videos. Therefore, it has become a significant research problem in short videos to figure out how to get audiences to watch short videos on a regular basis while avoiding side effects like anxiety and addiction and improving audiences' subjective well-being. Based on the theory of Internet addiction, this study analyzed short video users using the 2×2×2 research method and explored the relationship between the length of use, addiction, anxiety, and subjective well-being of short video users. The results showed that short video users with different usage lengths showed significant differences in addiction, anxiety, subjective well-being, and online social support; innovative different short video users showed significant differences in addiction and anxiety, as well as a triadic relational interaction of short video users' anxiety under the interaction with self-efficacy and online social support. This study contributes to the advancement of internet addiction theory research and application, assisting short video users in avoiding addiction and anxiety, and improving the subjective well-being of short video users, thereby promoting the growth of the short video industry.

• 한국멀티미디어학회논문지
• /
• 제18권9호
• /
• pp.1047-1057
• /
• 2015

In this paper, we propose an effective wireless transmission technology, under poor wireless transmission channel surroundings caused by speedy flying, that are able to transmit high quality video recording information and surveillance data via accessing to various wireless networking services architecture such as One-on-One, Many-on-One, One-on-Many, Over the Horizon. The Real-Time Position Analysis(RAPA) method is also suggested to provide more meaningful video information of shooting area. The suggested wireless transmission technology and RAPA can make remote control of UAV's flight route to get valuable topography information. Because of the benefit to get both of video information and GPS data of shooting area simultaneously, the result of study can be applied to various application sphere including UAV that requires high speed wireless transmission.

• 한국콘텐츠학회논문지
• /
• 제16권5호
• /
• pp.35-45
• /
• 2016

본 연구는 현재 사용 중인 모바일 동영상 서비스의 사용자 만족 향상을 위한 기초자료를 제공하고자 속성별 만족도를 조사하고 성별 및 연령에 따라 속성별 만족도와 전반적 만족도와의 관련성을 분석하여 모바일 동영상 서비스 만족도에 영향을 미치는 요인을 분석하는 것을 목적으로 하고 있다. 이를 위해 DMB와 모바일 동영상 서비스를 동시에 사용하는 362명의 사용자를 대상으로 모바일 동영상 서비스의 전반적 만족도에 영향을 미치는 요인들을 분석하였다. 또한 속성별 만족도와 전반적 만족도간 관계에 지상파콘텐츠 제공여부가 조절효과를 하는지를 분석하였다. 분석방법으로 빈도분석, 교차분석, t-test/F-test, 다중회귀분석, 조절회귀분석을 실시하였다. 연구결과 모바일 동영상 서비스 전반적 만족도에 영향을 미치는 요인으로는 콘텐츠 다양성, 화질, 재생품질, 이용편리성, 데이터 소모량 등 이었으며 성별, 연령별로 속성별 요인과 영향력에 있어서 차이가 있었다. 또한 지상파 콘텐츠 제공여부는 전반적 만족도에 영향을 미치는 결정변수 및 조절변수로 작용하지 않는 것으로 나타났다. 그러므로 만족도를 향상시키기 위해서는 반드시 지상파 콘텐츠를 제공하기 보다는 다양한 콘텐츠 제공과 UI/UX 개선 등 이용편리성을 개선해주는 것이 바람직한 방법임을 확인하였다. 이러한 결과를 바탕으로 시사점과 한계점을 제시하였다.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.215-220
• /
• 2022

Emotion recognition is one of the most important and challenging areas of computer vision. Nowadays, many studies on emotion recognition were conducted and the performance of models is also improving. but, more research is needed on emotion recognition and sentiment analysis of video viewers. In this paper, we propose an emotion analysis system the includes a sentiment analysis model and an interest prediction model. We analyzed the emotional patterns of people watching popular and unpopular videos and predicted the level of interest using the emotion analysis system. Experimental results showed that certain emotions were strongly related to the popularity of videos and the interest prediction model had high accuracy in predicting the level of interest.

• 문화기술의 융합
• /
• 제2권2호
• /
• pp.23-27
• /
• 2016

색청은 성장기에 프루닝이 정상적으로 이루어지지 않아서 시각이나 청각 경로에 혼선이 생긴 사람들에게 발생한다. 그들이 겪는 현상을 '색청'이라고 부른다 색청은 소리를 들을 때 색을 보는 형상을 말한다. 영상의 인터뷰에서 예술분야 전문가는 천부적인 재능으로 보았으며, 의학 분야 전문가는 일상생활에 큰 혼란을 야기하는 장애가 될 수 있다고 말한다. 일반적으로 사람들은 무의식적으로 공감각현상을 겪고 있다. 본 논문에서는 영상의 결과물을 바탕으로 과학적으로 증명된 연구결과와 일상 속의 현상을 바탕으로 '색청'을 분석하고, 또한 편집자의 관점에서 영상을 분석한다.