• Journal of Korea Multimedia Society
• /
• v.21 no.3
• /
• pp.400-414
• /
• 2018

It is required for today's video contents to interact with a viewer in order to provide more personalized experience to viewer(s) than before. In order to do so by providing friendly experience to a viewer from video contents' systemic perspective, understanding and analyzing the situation of the viewer have to be preferentially considered. For this purpose, it is effective to analyze the situation of a viewer by understanding the state of the viewer based on the viewer' s behavior(s) in the process of watching the video contents, and classifying the behavior(s) into the viewer's emotion and state during the flow. The term 'Flow-emotion-state' presented in this study is the state of the viewer to be assumed based on the emotions that occur subsequently in relation to the target video content in a situation which the viewer of the video content is already engaged in the viewing behavior. This Flow-emotion-state of a viewer can be expected to be utilized to identify characteristics of the viewer's Flow-situation by observing and analyzing the gesture and the facial expression that serve as the input modality of the viewer to the video content.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.3
• /
• pp.78-87
• /
• 2002

A macroblock(MB) in MPEG coded domain can have zero, one, or two motion vectors depending on its frame type and prediction direction (forward-, backward-, or hi-directionally). In this paper, we propose a method that converts these motion vectors on MPEG coded domain as a uniform set, independent of the frame type and the direction of prediction, and directly utilizes these re-analyzed motion vectors for understanding video contents. Also, using this frame-type-independent motion vector, we propose novel methods for detecting and tracking moving objects with frame-based detection accuracy on the compressed domain. These algorithms are performed directly from the MPEG bitstreams after VLC decoding with little time consumption. Experimental results show validity and outstanding performance of our methods.

• The Journal of Art Theory & Practice
• /
• no.13
• /
• pp.185-213
• /
• 2012

Charles Stankievech's 2011 installation LOVELAND includes a wall-sized screen depicting video footage of a barren arctic landscape in an enclosed room, painted and bathed in white light, that appears as an extension of the imaged environment. A melodic and industrial musical score emanates from multiple sound panels and as the music increases a cloud of purple smoke becomes visible on the horizon line in the distance and gradually advances toward the viewer until it completely fills the screen. The smoke then remains, rushing about madly and lapping at the border between the screen and the room before it suddenly subsides and the spectator is again left with the desolate landscape. The entire process takes a mere five minutes and then, fixed on an endless loop, begins again. This paper positions LOVELAND as an attempt to simulate a sublime experience of the end of the world through a transposition of the Arctic atmosphere into the gallery space. Encompassing a discussion of the historical and contemporary significance of the Arctic in popular culture, aesthetics and environmental politics, it is suggested that Stankievech employs an apocalyptic trope in reference to the unstable position of the North in the current political and ecological climate. Revisiting critiques of modernist exhibition practices and investigating the perceptual and temporal dimensions of the work, this analysis focuses primarily on the experience of the installation's spectator. Visually, aurally and phenomenologically immersed, the viewer is made subject to, and implicated in, the events unfolding on the screen and within the space. Due to the looping of the video footage, this paper argues that the apocalypse imaged in LOVELAND is presented as an endless event - incessantly enacted, yet infinitely deferred - and that the spectator is enveloped in an uncertain and unceasingly extended present moment.

• Journal of the Korean Society of Costume
• /
• v.55 no.8 s.99
• /
• pp.112-126
• /
• 2005

The purpose of this study is to analyze the aesthetic characteristics of 'movement' expression in modern fashion(1910-2004) based on a study of modern fine arts which adopted 'movement' element in their work. In this study the meaning of movement was defined as motion, changing position and transformation. Literature survey through books and research papers and demonstrative study with fashion collection photos were undertaken. The results wert as follows ; 1) Kinetic art, optical an, light kinetic art and technology art such as video and computer art have adopted 'movement' element in their work. 2) The plasticities of 'movement' fine arts were identified as mutual penetration, increase of visibility, use of non-traditional materials and dynamism. The internal meanings were identified as expansion of aesthetic experience and the concept of fine art, optimistic attitude on technology, spectator participation and integration of art and life. 3) The 'movement' expression in modern fashion was distinctively found in 1910s-20s(avant-garde fashion), 1960s (kinetic and optical art fashion) and mid 1990s to 2004 (techno-cyber fashion). 4) The plasticities of the 'movement' expression in modern fashion were identified as non-definition, use of non-traditional materials, dynamism. The internal meanings were identified as expansion of aesthetic experience and the concept of dress, optimistic attitude on technology, playfulness through participation. In conclusion, the expression of 'movement' in modern fashion has optimistic viewpoint on the development of modern society and is one of the interesting design points which will be pursued in the fellowing years.

• The Journal of the Korea Contents Association
• /
• v.7 no.10
• /
• pp.80-88
• /
• 2007

Applying Visual Art to pop music performance is gradually increasing. A video editor which simply mixes a number of images was mainly used in the past, but now various computer software make it easy to control visual art by development of computer technology, and it became possible for you to express unique and inimitable idea as well. Compare that a complicated equipment which makes them spend much expense and time was only used in the big size of concert hall in early days, a small and simple one now helps you easily apply your idea to Visual art in Pop music performance even in the small club. The technic of Visual art is being developed gradually especially by using computer The point of this study is how to apply real-time interaction between sound and visual image to interactive media art.

• ETRI Journal
• /
• v.32 no.4
• /
• pp.566-576
• /
• 2010

In a multiview video system, interactivity is important for users and should be considered in the design of multiview video coding (MVC). In this paper, we present an interactivity evaluation model for MVC schemes by using both weighted random graph and Markov approaches. The main factors that affect both the interactivity and rate-distortion (RD) performances of MVC schemes are analyzed and discussed in detail. By taking these factors into consideration, a new MVC scheme is proposed for high interactivity and RD gains. Experimental results show that the proposed scheme has a significant interactivity gain with little coding loss, compared to the state-of-the-art benchmark. As an extension to RD performance analysis, the interactivity evaluation model can be used as a design tool of alternative schemes for a future interactive multiview video system.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.86-91
• /
• 2024

In the field of artistic creation, the iterative development of AI-generated video software has pushed the boundaries of multimedia content creation and provided powerful creative tools for non-professionals. This paper extensively examines two leading AI-generated video software, PIKA Labs and RUNWAY, discussing their functions, performance differences, and application scopes in the video generation domain. Through detailed operational examples, a comparative analysis of their functionalities, as well as the advantages and limitations of each in generating video content, is presented. By comparison, it can be found that PIKA Labs and RUNWAY have excellent performance in stability and creativity. Therefore, the purpose of this study is to comprehensively elucidate the operating mechanisms of these two AI software, in order to intuitively demonstrate the advantages of each software. Simultaneously, this study provides valuable references for professionals and creators in the video production field, assisting them in selecting the most suitable tools for different scenarios, thereby advancing the application and development of AI-generated video software in multimedia content creation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.280-282
• /
• 2005

In this paper we propose several mapping schemes for streaming video generated by state-of-the-art H.264 codec over IEEE 802.11e enabled wireless LANs. The schemes take advantage of both 802.11e's QoS mechanism and some novel features of the H.264 codec, so as to protect the most important information in terms of visual quality and reduce distortion under network congestion. The proposed methods are evaluated by means of the H.264 reference software codec, network simulation, and objective video quality measurements. Results show that the proposed methods achieve a robust and error resilient H.264 video streaming over wireless LANs than traditional best-effort streaming.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2754-2768
• /
• 2013

Video fingerprints generated from global features are usually vulnerable against general geometric transformations. In this paper, a novel video fingerprinting algorithm is proposed, in which a new spatio-temporal gradient is designed to represent the spatial and temporal information for each frame, and a new partition scheme, based on concentric circle and rings, is developed to resist the attacks efficiently. The centroids of spatio-temporal gradient orientations (CSTGO) within the circle and rings are then calculated to generate a robust fingerprint. Our experiments with different attacks have demonstrated that the proposed approach outperforms the state-of-the-art methods in terms of robustness and discrimination.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.42-45
• /
• 2010

This paper proposes an intelligent video surveillance system for human object tracking. The proposed system integrates the object extraction, human object recognition, face detection, and camera control. First, the object in the video signals is extracted using the background subtraction. Then, the object region is examined whether it is human or not. For this recognition, the region-based shape descriptor, angular radial transform (ART) in MPEG-7, is used to learn and train the shapes of human bodies. When it is decided that the object is human or something to be investigated, the face region is detected. Finally, the face or object region is tracked in the video, and the pan/tilt/zoom (PTZ) controllable camera tracks the moving object with the motion information of the object. This paper performs the simulation with the real CCTV cameras and their communication protocol. According to the experiments, the proposed system is able to track the moving object(human) automatically not only in the image domain but also in the real 3-D space. The proposed system reduces the human supervisors and improves the surveillance efficiency with the computer vision techniques.