• Information and Communications Magazine
• /
• v.25 no.12
• /
• pp.10-18
• /
• 2008

In this paper, we present a low-power design of H.264 codec based on dedicated hardware and software solution on EMP(ETRI Multi-core platform). The dedicated hardware scheme has reducing computation using motion estimation skip and reducing memory access for motion estimation. The design reduces data transfer load to 66% compared to conventional method. The gate count of H.264 encoder and the performance is about 455k and 43Mhz@30fps with D1(720x480) for H.264 encoder. The software solution is with ASIP(Application Specific Instruction Processor) that it is SIMD(Single Instruction Multiple Data), Dual Issue VLIW(Very Long Instruction Word) core, specified register file for SIMD, internal memory and data memory access for memory controller, 6 step pipeline, and 32 bits bus width. Performance and gate count is 400MHz@30fps with CIF(Common Intermediated format) and about 100k per core for H.264 decoder.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5361-5374
• /
• 2016

Combining channel coding and network coding in a physical layer in a fading channel, generalized joint channel-network coding (G-JCNC) is proved to highly perform in a two-way relay channel (TWRC). However, most relevant discussions are restricted to symmetric networks. This paper investigates the G-JCNC protocols in an asymmetric TWRC (A-TWRC). A newly designed encoder used by source nodes that is dedicated to correlate codewords with different orders is presented. Moreover, the capability of a simple common non-binary decoder at a relay node is verified. The effects of a power match under various numbers of iteration and code lengths are also analyzed. The simulation results give the optimum power match ratio and demonstrate that the designed scheme based on G-JCNC in an A-TWRC has excellent bit error rate performance under an appropriate power match ratio.

• ETRI Journal
• /
• v.26 no.2
• /
• pp.122-135
• /
• 2004

Although frame-based MPEG-4 video services have been successfully deployed since 2000, MPEG-4 video coding is now facing great competition in becoming a dominant player in the market. Object-based coding is one of the key functionalities of MPEG-4 video coding. Real-time object-based video encoding is also important for multimedia broadcasting for the near future. Object-based video services using MPEG-4 have not yet made a successful debut due to several reasons. One of the critical problems is the coding complexity of object-based video coding over frame-based video coding. Since a video object is described with an arbitrary shape, the bitstream contains not only motion and texture data but also shape data. This has introduced additional complexity to the decoder side as well as to the encoder side. In this paper, we have analyzed the current MPEG-4 video encoding tools and proposed efficient coding technologies that reduce the complexity of the encoder. Using the proposed coding schemes, we have obtained a 56 percent reduction in shape-coding complexity over the MPEG-4 video reference software (Microsoft version, 2000 edition).

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.1
• /
• pp.269-274
• /
• 2023

In this paper, we proposed a new UNet 3+ model for medical image segmentation. The proposed ensemble(E) UNet 3+ model consists of UNet 3+s of varying depths into one unified architecture. UNet 3+s of varying depths have same encoder, but have their own decoders. They can bridge semantic gap between encoder and decoder nodes of UNet 3+. Deep supervision was used for learning on a total of 8 nodes of the E-UNet 3+ to improve performance. The proposed E-UNet 3+ model shows better segmentation results than those of the UNet 3+. As a result of the simulation, the E-UNet 3+ model using deep supervision was the best with loss function values of 0.8904 and 0.8562 for training and validation data. For the test data, the UNet 3+ model using deep supervision was the best with a value of 0.7406. Qualitative comparison of the simulation results shows the results of the proposed model are better than those of existing UNet 3+.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.721-723
• /
• 2020

부분 공간 군집화는 고차원 데이터에서 의미 있는 특징들을 선별 및 추출하여 저차원의 부분 공간에서 군집화 하는 것이다. 그러나 최근 딥러닝 활용한 부분 공간 군집화 연구들은 AutoEncoder을 기반으로 의미있는 특징을 선별하는 것이 아닌 특징 맵의 크기를 증가시켜서 네트워크의 표현 능력에 중점을 둔 연구되고 있다. 본 논문에서는 AutoEncdoer 네트워크에 Channel Attention 모델을 활용하여 Encoder와 Decoder에서 부분 공간 군집화를 위한 특징을 강조하는 네트워크를 제안한다. 본 논문에서 제안하는 네트워크는 고차원의 이미지에서 부분 공간 군집화를 위해 강조된 특징 맵을 추출하고 이를 이용해서 보다 향상된 성능을 보여주었다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.333-338
• /
• 2019

인코더-디코더(Encoder-decoder)는 현대 기계 번역(Machine translation)의 가장 기본이 되는 모델이다. 인코딩은 마치 인간의 뇌가 출발어(Source language) 문장을 읽고 이해를 하는 과정과 유사하고, 디코딩은 뇌가 이해한 의미를 상응하는 도착어(Target language) 문장으로 재구성하는 행위와 비슷하다. 그렇다면 벡터로 된 인코더 표현은 문장을 읽고 이해함으로써 변화된 뇌의 상태에 해당한다고 볼 수 있다. 사람이 어떤 문장을 잘 번역하기 위해서는 그 문장에 대한 이해가 뒷받침되어야 하는 것처럼, 기계 역시 원 문장이 가진 의미를 제대로 인코딩해야 향상된 성능의 번역이 가능할 것이다. 본 논문에서는 뇌과학에서 뇌 동기화(Brain-to-brain coupling)라 일컫는 현상을 모방해, 출발어와 도착어의 공통된 의미를 인코딩하여 기계 번역 성능 향상에 도움을 줄 수 있는 이중 번역 기법을 소개한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1579-1588
• /
• 2014

The LAN method is the most widely used in domestic high-speed internet access and rapidly moving to 1 Gbps Ethernet from 100 Mbps one to provide high-speed services such as UHD TV. The 1000BASE-T PHY with 4 pairs UTP transmits a PAM-5 signal at the 125 MHz clock per each pair to achieve 1 Gbps rate. In order to correct errors over the channel, the transmitter uses a TCM which is combined the convolutional encoder and PAM-5, and the receiver uses the Viterbi decoder. In this paper, we implement a Viterbi decoder which can correct two pair errors and operate at the least 125 MHz clock speed. Finally, we will verify the error correction function and the operating speed of the implemented decoder with a logic analyzer.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.24 no.3
• /
• pp.63-72
• /
• 1999

Recent studies on the Constant Bit Rate and Variable Bit Rate transmissions have mainly focused on the frame by frame encoder rate control based on the quantization parameter. With the existing approaches it is difficult to guarantee a consistent video quality. Also, the rate control overhead is too high for the real-time video sources. In this paper, a channel rate allocation scheme based on the control period is proposed to transmit a real-time video, in which the control period is defined by a pre-specified number of frames or group of pictures. At each control period, video traffic information is collected to determine the channel rate at the next control period. The channel rate is allocated to satisfy various channel rate constraints such that the buffer occupancy at the decoder is maintained at a target level. If the allocated channel rate approaches the level at which the negotiated traffic descriptions may be violated, the encoder rate is decreased through adjusting quantization parameters in the MPEG encoder. In the experimental results, the video quality and the overflow and underflow probabilities at the buffer are compared at different control periods. Experiments show that the video quality and the utilization of network bandwidth resources can be optimized through the suitable selection of the control period.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.2
• /
• pp.95-100
• /
• 2002

By feedback channel, the decoder reports the addresses of corrupted macroblocks induced by transmission errors back to the encoder With these negative acknowledgements, the encoder can make the next frame having propagated errors by using forward dependency based on GOBs and MBs of the frame happening transmission errors. The encoder can precisely calculate and track the propagated errors by examining the backward motion dependency for each of four comer pixels in the current encoding frame until before-mentioned the next frame. The error-propagation effects can be terminated completely by INTRA refreshing the affected macroblocks. Such a fast algorithm further reduce the computation and memory requirements. The advantages of the low computation complexity and the low memory requirement are Particularly suitable for real-time implementation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.97-99
• /
• 2022

For the early identification and treatment of colorectal cancer, accurate polyp segmentation is crucial. However, polyp segmentation is a challenging task, and the majority of current approaches struggle with two issues. First, the position, size, and shape of each individual polyp varies greatly (intra-class inconsistency). Second, there is a significant degree of similarity between polyps and their surroundings under certain circumstances, such as motion blur and light reflection (inter-class indistinction). U-net, which is composed of convolutional neural networks as encoder and decoder, is considered as a standard for tackling this task. We propose an updated U-net architecture replacing the encoder part with vision transformer network for polyp segmentation. The proposed architecture performed better than the standard U-net architecture for the task of polyp segmentation.