• Journal of information and communication convergence engineering
• /
• v.20 no.4
• /
• pp.288-294
• /
• 2022

The media content market has been growing, as various types of content are being mass-produced owing to the recent proliferation of the Internet and digital media. In addition, platforms that provide personalized services for content consumption are emerging and competing with each other to recommend personalized content. Existing platforms use a method in which a user directly inputs video metadata. Consequently, significant amounts of time and cost are consumed in processing large amounts of data. In this study, keyframes and audio spectra based on the YCbCr color model of a movie trailer were extracted for the automatic generation of metadata. The extracted audio spectra and image keyframes were used as learning data for genre recognition in deep learning. Deep learning was implemented to determine genres among the video metadata, and suggestions for utilization were proposed. A system that can automatically generate metadata established through the results of this study will be helpful for studying recommendation systems for media super-personalization.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.287-293
• /
• 2023

With the rapid development of domestic and international over-the-top markets, a large amount of video content is being created. As the volume of video content increases, consumers tend to increasingly check data concerning the videos before watching them. To address this demand, video summaries in the form of plot descriptions, thumbnails, posters, and other formats are provided to consumers. This study proposes an approach that automatically generates posters to effectively convey video content while reducing the cost of video summarization. In the automatic generation of posters, face recognition and clustering are used to gather and classify character data, and keyframes from the video are extracted to learn the overall atmosphere of the video. This study used the facial data of the characters and keyframes as training data and employed technologies such as DreamBooth, a text-to-image generation model, to automatically generate video posters. This process significantly reduces the time and cost of video-poster production.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.102-107
• /
• 2005

With the advancement which development and information communication of the computer is quick about lower with multimedia technical diffusion of network base the necessity the use of the digital image technique which is various regarding the protection of sharp increasing multimedia contents raised its head in the social whole. the copyright protection against a multimedia data hazard the authentication techniques it will be able to confirm the content authentication, ownership authentication, illegal copy of the image which stands is demanded. confronts to the water marking technique of existing and the researches the fact that against a picture is most. In this paper, It does not damage the video data which is a multimedia contents not to be, it inserts copyright information and it protects the right of ownership. It is with a copyright protection which leads the wavelet transform which is a watermark of frequency base from visual system viewpoint in the human being center with it proposes the watermarking technique against a forgery prevention.

• The Journal of the Korea Contents Association
• /
• v.8 no.7
• /
• pp.120-127
• /
• 2008

Practical use degree of Motion Capture technology is low in korea game market which did growth of MMORPG putting first. However, that is dance game or FPS, sports game genre is magnified. Therefore, practical use degree of Motion Capture technology is increasing. And, need various research to take advantage of Motion Capture technology effectively. Studied 3D game character animation manufacture pipe line for it. Characteristic of this manufacture pipe line is work classification, correction of two times, Biped format all-in-one to progress Motion Capture technology and keyframe-animation work at the same time. Also, manufacture pipe line that is consisted of this constituent has economic performance, extensity, systemicity.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.10
• /
• pp.796-800
• /
• 2009

Currently, there are many software tools that can generate 3D human figure models and animations based on the advancement of computer graphics technology. However, we still have problems in interoperability of human data models in different applications because common data models do not exist. To address this issue, the Web3D Consortium and the ISO/IEC JTC1 SC24 WG6 have developed the H-Anim standard. However, H-Anim does not include human motion data formats although it defines the structure of a human figure. This research is intended to obtain interoperable human animation by defining the data for human motions in H- Anim figures. In this paper, we describe a syntactic method to define motion data for the H-Anim figure and its implementation. In addition, we describe a method of specifying motion parameters necessary for generating animations by using an arbitrary character model data set created by a general graphics tool.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.12
• /
• pp.1834-1843
• /
• 2016

DVRs are the most common recording and displaying devices used for surveillance. Video compression plays a key role in DVRs for saving storage; the video compression standard, H.264/AVC, has recently become the dominant choice for DVRs. DVRs require various display modes, such as fast-forward, backward play, and pause; these are called trick modes. The implementation of precise trick mode play requires a very high decoding capability or a very intelligent scheme in order to handle the high computation complexity. The complexity is increased in many surveillance applications where more than one camera is used to monitor multiple spots or to monitor the same area using various angles. An implementation of a trick mode play and a frame buffer management scheme for the hardware-based H.264/AVC codec for multi-channel is presented in this paper. The experimental results show that exact trick mode play is possible using a standard H.264/AVC video codec with keyframe encoding feature at the expense of bitstream size increase.

• Journal of Broadcast Engineering
• /
• v.13 no.5
• /
• pp.662-676
• /
• 2008

This paper presents a video copy detection algorithm that blocks online transfer of illegally copied DTV broadcast programs. Particularly, the proposed algorithm establishes a set of keyframes by detecting abrupt changes of luminance, and then exploits the spatio-temporal features of keyframes. Comparing with the preregistered features stored in the database of DTV broadcast programs, the proposed scheme performs a function of video filtering in order to distinguish whether an uploaded video is illegally copied or not. Note that we analyze only a set of keyframes instead of an entire video frame. Thus, it is highly efficient to identify illegal copied video when we deal with a vast size of broadcast programs. Also, we confirm that the proposed technique is robust to a variety of video edit-effects that are often applied by online video redistribution, such as apsect-ratio change, logo insertion, caption insertion, visual quality degradation, and resolution change (downscaling). In addition, we perform a benchmark test in which the proposed scheme outperforms previous techniques.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.4 no.2
• /
• pp.108-115
• /
• 2009

Thanks to the development of computer graphics, Animation can be easily accessed through movies or games. The users can meet various contents and are asking for high quality animations that resembles reality to a near perfection. The research is proceeded to observe the fish shapes and swimming movements through cyber aquariums, fish ecology museums and fish encyclopedias. The core of expressing undersea scenery is the natural and dynamic movements of the fish. In this thesis in order to achieve the natural shape of fish swimming, it is necessary to design a fish growth process system based on environmental factors and apply different standard points depending on the various swimming types of fish species to express the fish as near reality as possible. And by calculating the different swimming velocities of different standard points, a natural swimming shape will be achieved.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.3035-3041
• /
• 2014

The steadicam effects is widely used in production of the 3D animation for natural camera movement. Conventional method for steadicam effects is using keyframe animation technique, which is annoying and time consuming process. Furthermore it is difficult and unnatural to simulate camera movement in real world. In this paper we propose a novel method for representing steadicam effects on virtual camera of 3D animation. We modeled a camera of real world into Maya production tools, considering gravity, mass and elasticity. The model is implemented with Python language, which is directly applied to Maya platform as a filter module. The proposed method reduces production time and improves production environment. It also makes more natural and realistic footage to maximize visual effects.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1716-1722
• /
• 2021

Recently, the capacity of video content delivery services has been increasing significantly. Therefore, the importance of user recommendation is increasing. In addition, these contents contain a variety of characteristics, making it difficult to express the characteristics of the content properly only with a few keywords(Elements used in the search, such as titles, tags, topics, words, etc.) specified by the user. Consequently, existing recommendation systems that use user-defined keywords have limitations that do not properly reflect the characteristics of objects. In this paper, we compare the efficiency of between a method using voice data-based subtitles and an image comparison method using keyframes of images in recommendation module of educational video service systems. Furthermore, we propose the types and environments of video content in which each analysis technique can be efficiently utilized through experimental results.