• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4476-4491
• /
• 2021

Video service providers tend to face user network problems in the process of transmitting video streams. They strive to provide user with superior video quality in a limited bitrate environment. It is necessary to accurately determine the target bitrate range of the video under different quality requirements. Recently, several schemes have been proposed to meet this requirement. However, they do not take the impact of visual influence into account. In this paper, we propose a new multi-category model to accurately predict the target bitrate range with target visual quality by machine learning. Firstly, a dataset is constructed to generate multi-category models by machine learning. The quality score ladders and the corresponding bitrate-interval categories are defined in the dataset. Secondly, several types of spatial-temporal features related to VMAF evaluation metrics and visual factors are extracted and processed statistically for classification. Finally, bitrate prediction models trained on the dataset by RandomForest classifier can be used to accurately predict the target bitrate of the input videos with target video quality. The classification prediction accuracy of the model reaches 0.705 and the encoded video which is compressed by the bitrate predicted by the model can achieve the target perceptual quality.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.969-972
• /
• 2016

In this paper, we propose an algorithm of angular mode selection for high-performance HEVC intra prediction. HEVC intra prediction is used to remove the spatial redundancy. Intra prediction has a total of 35 modes and block size of $64{\times}64$ to $4{\times}4$. Intra prediction has a high amount of calculation and operational time due to performing all 35 modes for each block size for the best cost. The angular mode algorithm proposed has a simple difference between pixels of the original image and the selected angular mode. A decision is made to select one angular mode plus planar mode and DC mode to perform the intra prediction and determine the mode with the best cost. In effect, only three modes are executed compared to the traditional 35 modes. Performance evaluation index used are BD-PSNR and BD-Bitrate. For the proposed algorithm, BD-PSNR results averagely increased by 0.035 and BD-Bitrate decreased by 0.623 relative to the HM-16.9 intra prediction. In addition, the encoding time is decreased by about 6.905%.

• ETRI Journal
• /
• v.38 no.6
• /
• pp.1064-1073
• /
• 2016

An adaptive speech streaming method to improve the perceived speech quality of a software-based multipoint control unit (SW-based MCU) over IP networks is proposed. First, the proposed method predicts whether the speech packet to be transmitted is lost. To this end, the proposed method learns the pattern of packet losses in the IP network, and then predicts the loss of the packet to be transmitted over that IP network. The proposed method classifies the speech signal into different classes of silence, unvoiced, speech onset, or voiced frame. Based on the results of packet loss prediction and speech classification, the proposed method determines the proper amount and bitrate of redundant speech data (RSD) that are sent with primary speech data (PSD) in order to assist the speech decoder to restore the speech signals of lost packets. Specifically, when a packet is predicted to be lost, the amount and bitrate of the RSD must be increased through a reduction in the bitrate of the PSD. The effectiveness of the proposed method for learning the packet loss pattern and assigning a different speech coding rate is then demonstrated using a support vector machine and adaptive multirate-narrowband, respectively. The results show that as compared with conventional methods that restore lost speech signals, the proposed method remarkably improves the perceived speech quality of an SW-based MCU under various packet loss conditions in an IP network.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.401-410
• /
• 2019

In this paper, we propose a reference picture generation method for Inter-layer prediction based deep learning to improve the SHVC coding performance. A description will be given of a structure for performing filtering using a VDSR network on a DCT-IF based upsampled picture to generate a new reference picture and a training method for generating a reference picture between SHVC Inter-layer. The proposed method is implemented based on SHM 12.0. In order to evaluate the performance, we compare the method of generating Inter-layer predictor by applying dictionary learning. As a result, the coding performance of the enhancement layer showed a bitrate reduction of up to 13.14% compared to the method using dictionary learning, a bitrate reduction of up to 15.39% compared to SHM, and a bitrate reduction of 6.46% on average.

• ETRI Journal
• /
• v.31 no.5
• /
• pp.610-612
• /
• 2009

We present intra-mixture prediction (IMP) mode for intra prediction and an enhanced estimation method for most probable mode (MPM). IMP mode supports more flexibility in intra prediction by mixing $4{\times}4$ blocks and $8{\times}8$ blocks in one macroblock, while the enhanced MPM estimation extends the number of referenced neighboring blocks and efficiently uses their prediction modes depending on their positions. Simulation results show that the combination of both proposed methods provides a bit reduction in the Bj${\phi}$ntegaard delta bitrate by an average of 2.56% compared to H.264/AVC.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.405-408
• /
• 2017

Based on the fact that high similarities exist between viewpoints of multi-view images, MV-HEVC achieves high encoding efficiency by performing conventional temporal direction prediction in a single viewpoint as well as inter-view prediction between viewpoints. In this paper, we propose to integrate SHVC and MVC (Multi-view Video Coding) to implement scalable multi-view video encoder using HEVC as a base layer. According to experimental results, it is verified that the BD-PSNR improvement reaches up to 1.5dB while reducing the BD-Bitrate by around 50~60%.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.525-528
• /
• 2005

Adaptive streaming algorithm for the realtime video decoder that can be dynamically adaptable to the network channel status or terminal environment is described and performance analyzed. An LMS filter is used to predict the bitrate and predicted bitrate is used to optimize based prediction filter is used to adapt and optimize the quality of the decoded pictures. The quality of the output pictures are about 48dB.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.7
• /
• pp.14-23
• /
• 1993

This paper proposes an algorithm to reduce the bitrate for transmission of MCP(motion compensated prediction) error signals. Many digital image coders have recently employed hybrid coding schemes which perform motion compensation, DCT transform, quantization, and variable length coding. The variable length coding compresses the quantized DCT coefficient data by removing their statistical redundancy. But some DCT blocks have the interblock statistical redundancy as well as the intrablock one. To utilize both of them, the DCT blocks are classified into the interleaving group and the non-interleaving group. And then each DCT blocks in the interleaving group are is encoded independently, and the DCT blocks in the interleaving group are encoded after interleaving the DCT coefficients. Through the simulations, it is shown that the proposed method outperforms the conventional method in which each DCT block is encoded independently.

• Journal of Broadcast Engineering
• /
• v.17 no.5
• /
• pp.781-788
• /
• 2012

In HEVC, the fast search method is used for reducing the complexity of the motion prediction procedure. It is consisted of the sub-sampled SAD which reduce the complexity of Sum of Absolute Differences(SAD) calculation and the simplified bi-prediction method which reduce the iterations of the uni-prediction for the bi-prediction. The computational complexity is largely decreased by the fast search method but the coding gain is also decreased. In this paper, the simplified bi-prediction is extended to compensate the performance loss and the prediction cost based complexity reduction methods are also proposed to reduce the complexity burden by the extended bi-prediction method. A prediction cost based complexity reduction method is consisted of early termination method for the extended bi-prediction and the bi-prediction skipping method. Compare with HM 6.0 references S/W, the average 0.42% of BD-bitrate is decreased by both the extended bi-prediction method and the prediction cost based complexity reduction methods with negligible increasement of the complexity.

• ETRI Journal
• /
• v.34 no.1
• /
• pp.106-109
• /
• 2012

In this letter, we propose a new prediction block filter that can reduce errors between the original and prediction blocks. The proposed filter adaptively adjusts filter coefficients by using the previously reconstructed adjacent blocks and their prediction blocks. Then, the filter is selectively applied to the current prediction block according to the rate-distortion optimization. Moreover, since the same filter coefficients can be derived in the decoder, they are not encoded into the bit-stream. The proposed method achieves a 4.65% bitrate saving on average compared with H.264/AVC.