• Journal of Korea Game Society
• /
• v.18 no.2
• /
• pp.89-98
• /
• 2018

The recent Neural Network technique has shown good performance in content generation such as image generation in addition to the conventional classification problem and clustering problem solving. In this study, we propose an image generation method using artificial neural network as a next generation content creation technique. The proposed artificial neural network model receives two images and combines them into a new image by taking color from one image and shape from the other image. This model is made up of Convolutional Neural Network, which has two encoders for extracting color and shape from images, and a decoder for taking all the values of each encoder and generating a combination image. The result of this work can be applied to various 2D image generation and modification works in game development process at low cost.

• Journal of KIISE:Information Networking
• /
• v.35 no.6
• /
• pp.510-520
• /
• 2008

These days, the network convergence for utilizing heterogeneous network on mobile device is being very actively studied. However, understanding characteristics of physical network interfaces and video encoder is needed for using the network convergence technologies efficiently. Thus, this paper proposes an optimized method for streaming video data through different network paths depending on data characteristics and channel condition. Accordingly, unlike the traditional methods, this study divides scalable coded videos by layer importance, the importance of stream information, and the importance in consideration of video decoder's robustness and selectively sends the data via multiple channels. And the experimental results show over 1dB increment in PSNR. The result of this study will provide an optimized video transmission technique in the next generation network convergence environment in which mobile devices have multiple network interfaces.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.7
• /
• pp.1355-1363
• /
• 2017

Recently, distributed compressed video sensing (DCVS) has been actively studied in order to achieve a low complexity video encoder by integrating both compressed sensing and distributed video coding characteristics. Conventionally, a motion compensated block compressed sensing with smoothed projected Landweber (MC-BCS-SPL) has been considered as an effective scheme of DCVS with all compressed sensing frames pursuing the simplest sampling. In this scheme, video frames are separately classified into key frames and WZ frames. However, when reconstructing WZ frame with conventional MC-BCS-SPL scheme at the decoder side, the visual qualities are poor for temporally active video sequences. In this paper, to overcome the drawbacks of the conventional scheme, an enhanced MC-BCS-SPL algorithm is proposed, which corrects the initial image with reference to the key frame using a high correlation between adjacent key frames. The proposed scheme is analyzed with respect to GOP (Group of Pictures) structuring method. Experimental results show that the proposed method performs better than conventional MC-BCS-SPL in rate-distortion.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.422-425
• /
• 2012

This paper proposes the CU-based approach for merge candidate list construction for providing reduced complexity and improved parallelism compared to the PU-based one. In the proposed method, a CU can have only one merge candidate list. So, Only one common merge candidate list is used for all PUs in a CU regardless of the PU partition type. The simulation results of proposed method showed that the encoder computational complexity was decreased by 3% to 6% and the decoder computational complexity was negligible change with the penalty of roughly 0.2% - 0.5% coding loss. The proposed method has several advantages: it provides simpler design, reduced complexity, and improved parallelism.

• Journal of Broadcast Engineering
• /
• v.10 no.1 s.26
• /
• pp.57-67
• /
• 2005

In the paper, we propose a TV-anytime codec that encodes and decodes TV-Anytime metadata according to the TV-Anytime specification so that the resulting binary TV-Anytime metadata can be transferred efficiently through the broadcasting network where the data bandwidth is restricted.. We describe the broadcasting environment that the TV-Anytime codec will be applied to, and the required functionalities of the software modules in detail. For the design of software modules, we show how to Implement the modules for metadata fragmentation. encoding, decoding, and the fragments management. The proposed TV-Anytime codec can be utilized as the core components to a personalized digital broadcasting system providing ECG(Electronic Content Guide) and segmentation information services according to TV-Anytime standard.

• Journal of Broadcast Engineering
• /
• v.6 no.2
• /
• pp.121-130
• /
• 2001

We propose an efficient DCT-domain video transcoding algorithm for flexible for bit-rate video communications. Video transcoding provides communication fiexibility by adaptively changing the bit-rate of compressed bit stream. During the transcoding process, adrift error is unavoidable because of the difference between reference images in the series of encoding and decoding. For solving the drift error problem, cascade pixel-domain transcoder (CPDT) has been proposed. CPDT, however, requires highly complex hardware and heavy computational overhead. In this paper we propose a DCT-domain transcoding technique, which enables efficient transcoding without any drift error. The proposed cascade DCT-domain transcoder (CDDT) is realized by new motion compensation and down-sampling methods in the DCT-domain.

• The Journal of the Korea Contents Association
• /
• v.12 no.4
• /
• pp.31-39
• /
• 2012

DVC(Distributed Video Coding) techniques have been attracting a lot of research works since these enable us to implement the light-weight video encoder and to provide good coding efficiency by introducing the feedback channel. However, the feedback channel causes the decoder to increase the decoding complexity and requires very high decoding latency because of numerous iterative decoding processes. So, in order to reduce the decoding delay and then to implement in a real-time environment, this paper proposes several parity bit estimation methods which are based on the temporal correlation, spatial correlation and spatio-temporal correlations between LDPCA frames on each bit plane in the consecutive video frames in pixel-domain Wyner-Ziv video coding scheme and then the performances of these methods are compared in fast DVC scheme. Through computer simulations, it is shown that the adaptive spatio-temporal correlation-based estimation method and the temporal correlation-based estimation method outperform others for the video frames with the highly active contents and the low active contents, respectively. By using these results, the proposed estimation schemes will be able to be effectively used in a variety of different applications.

• KIISE Transactions on Computing Practices
• /
• v.24 no.3
• /
• pp.138-144
• /
• 2018

A video is a vivid medium similar to human's visual-linguistic experiences, since it can inculcate a sequence of situations, actions or dialogues that can be told as a story. In this study, we propose story learning/regeneration frameworks from videos with successive event order supervision for contextual coherence. The supervision induces each episode to have a form of trajectory in the latent space, which constructs a composite representation of ordering and semantics. In this study, we incorporated the use of kids videos as a training data. Some of the advantages associated with the kids videos include omnibus style, simple/explicit storyline in short, chronological narrative order, and relatively limited number of characters and spatial environments. We build the encoder-decoder structure with successive event order embedding, and train bi-directional LSTMs as sequence models considering multi-step sequence prediction. Using a series of approximately 200 episodes of kids videos named 'Pororo the Little Penguin', we give empirical results for story regeneration tasks and SEOE. In addition, each episode shows a trajectory-like shape on the latent space of the model, which gives the geometric information for the sequence models.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9A
• /
• pp.694-701
• /
• 2003

In this paper, we present a hardware structure and new features of a smart antenna BTS (Base Transceiver Station) for CDMA2000 1X system. The proposed smart antenna BTS is a composite system consisting of many subsystems, i.e., array antenna element, frequency up/down converters, AD (Analog-to-Digital) and DA (Digital-to-Analog) converters, spreading/despreading units, convolutional encoder/Viterbi decoder, searcher, tracker, beamformer, calibration unit etc. Through the experimental tests, we found that the desired beam-pattern in both uplink and downlink communications is provided through the calibration procedure. Also it has been confirmed that the adaptive beamforming algorithm adopted to our smart antenna BTS is fast and accurate enough to support 4 fingers to each user. In our experiments, commercial mobile terminals operating PCS (Personal Communication System) band have been used. It has been confirmed that the smart antenna BTS tremendously improves the FER (Frame Error Rate) performance compared to the conventional 2-antenna diversity system.

• Journal of Digital Contents Society
• /
• v.3 no.2
• /
• pp.197-209
• /
• 2002

If we reduce the number of vertexes to decrease bit rate in polygon-based shape coding, the distortion of approximated contour increases rapidly. On the other hand, if we reduce the distortion, the number of vertexes increases rapidly and many bits are required to encode the vertexes. To improve this problem, in this paper we propose the approximation vertex search method. The encoder in the proposed method searches the type of distortion patterns that is the most similar to the shape which polygon edge and contour segment form and then encodes it. And then, the decoder mathematically finds the approximated vertexes from decoded distortion pattern information. Therefore, the proposed algorithm results in encoding many vertexes at a low bit rate and having the smoother shape than conventional method. As shown in computer simulation, the proposed method has less distortion than conventional method. It costs less bit rate by $10{\sim}20%$ than conventional algorithm in same distortion.