• Title/Summary/Keyword: 파이프라인 구조

Search Result 473, Processing Time 0.025 seconds

Design and Implementation of a Low-Complexity Real-Time Barrel Distortion Corrector for Wide-Angle Cameras (광각 카메라를 위한 저 복잡도 실시간 베럴 왜곡 보정 프로세서의 설계 및 구현)

  • Jeong, Hui-Seong;Kim, Won-Tae;Lee, Gwang-Ho;Kim, Tae-Hwan
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.50 no.6
    • /
    • pp.131-137
    • /
    • 2013
  • The barrel distortion makes serious problems in a wide-angle camera employing a lens of a short focal length. This paper presents a low-complexity hardware architecture for a real-time barrel distortion corrector and its implementation. In the proposed barrel distortion corrector, the conventional algorithm is modified so that the correction is performed incrementally, which results in the reduction of the number of required hardware modules for the distortion correction. The proposed barrel distortion corrector has a pipelined architecture so as to achieve a high-throughput correction. The correction rate is 74.86 frames per sec at the operating frequency of 314MHz in a $0.11{\mu}m$ CMOS process, where the frame size is $2048{\times}2048$. The proposed barrel distortion corrector is implemented with 14.3K logic gates.

(Theoretical Performance analysis of 12Mbps, r=1/2, k=7 Viterbi deocder and its implementation using FPGA for the real time performance evaluation) (12Mbps, r=1/2, k=7 비터비 디코더의 이론적 성능분석 및 실시간 성능검증을 위한 FPGA구현)

  • Jeon, Gwang-Ho;Choe, Chang-Ho;Jeong, Hae-Won;Im, Myeong-Seop
    • Journal of the Institute of Electronics Engineers of Korea SC
    • /
    • v.39 no.1
    • /
    • pp.66-75
    • /
    • 2002
  • For the theoretical performance analysis of Viterbi Decoder for wireless LAN with data rate 12Mbps, code rate 1/2 and constraint length 7 defined in IEEE 802.11a, the transfer function is derived using Cramer's rule and the first-event error probability and bit error probability is derived under the AWGN. In the design process, input symbol is quantized into 16 steps for 4 bit soft decision and register exchange method instead of memory method is proposed for trace back, which enables the majority at the final decision stage. In the implementation, the Viterbi decoder based on parallel architecture with pipelined scheme for processing 12Mbps high speed data rate and AWGN generator are implemented using FPGA chips. And then its performance is verified in real time.

Design and Implementation of IEEE 802.11i MAC Layer (IEEE 802.11i MAC Layer 설계 및 구현)

  • Hong, Chang-Ki;Jeong, Yong-Jin
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.34 no.8A
    • /
    • pp.640-647
    • /
    • 2009
  • IEEE 802.11i is an amendment to the original IEEE 802.11/b,a,g standard specifying security mechanism by stipulating RSNA for tighter security. The RSNA uses TKIP(Temporal Key Integrity Protocol) and CCMP(Counter with CBC-MAC Protocol) instead of old-fashioned WEP(Wired Equivalent Privacy) for data encryption. This paper describes a design of a communication security engine for IEEE 802.11i MAC layer. The design includes WEP and TKIP modules based on the RC4 encryption algorithm, and CCMP module based on the AES encryption algorism. The WEP module suffices for compatibility with the IEEE 802.11 b,a,g MAC layer. The CCMP module has about 816.7Mbps throughput at 134MHz, hence it satisfies maximum 600Mbps data rate described in the IEEE 802.11n specifications. We propose a pipelined AES-CCMP cipher core architecture, which has lower hardware cost than existing AES cores, because CBC mode and CTR mode operate at the same time.

The Design of High-Speed, High-Resolution D/A Converter for Digital Image Signal Processing with Deglitching Current Cell (글리치 방지 전류원을 이용한 고속 고정밀 디지탈 영상 신호 처리용 D/A 변환기 설계)

  • Lee, Seong-Dae;Jeong, Gang-Min
    • The Transactions of the Korea Information Processing Society
    • /
    • v.1 no.4
    • /
    • pp.469-478
    • /
    • 1994
  • In this paper, a high speed, high resolution information processing digital- analog converter was designed for high definition color graphic, digital image signal processing, HDTV. For high speed operation, matrix type current cell array, latch which is not use pipelined, and two dimensional structure decoder using transmission gate were designed. It is adopted to fast-conversion, low-power implementation and exhibited high performance at linearity and accuracy. To reduce silicon area and to maintain resolution, current cell array composed of weighted and non-weighted current cells. In this paper, deglitching current cell design for high accuracy, new switching algorithm assert to reduce switching error. It's This circuit dissipates 130W with a 5-V power supply, and operate above 100MHz with 10 bit resolution.

  • PDF

A 12b 200KHz 0.52mA $0.47mm^2$ Algorithmic A/D Converter for MEMS Applications (마이크로 전자 기계 시스템 응용을 위한 12비트 200KHz 0.52mA $0.47mm^2$ 알고리즈믹 A/D 변환기)

  • Kim, Young-Ju;Chae, Hee-Sung;Koo, Yong-Seo;Lim, Shin-Il;Lee, Seung-Hoon
    • Journal of the Institute of Electronics Engineers of Korea SD
    • /
    • v.43 no.11 s.353
    • /
    • pp.48-57
    • /
    • 2006
  • This work describes a 12b 200KHz 0.52mA $0.47mm^2$ algorithmic ADC for sensor applications such as motor controls, 3-phase power controls, and CMOS image sensors simultaneously requiring ultra-low power and small size. The proposed ADC is based on the conventional algorithmic architecture with recycling techniques to optimize sampling rate, resolution, chip area, and power consumption. The input SHA with eight input channels for high integration employs a folded-cascode architecture to achieve a required DC gain and a sufficient phase margin. A signal insensitive 3-D fully symmetrical layout with critical signal lines shielded reduces the capacitor and device mismatch of the MDAC. The improved switched bias power-reduction techniques reduce the power consumption of analog amplifiers. Current and voltage references are integrated on the chip with optional off-chip voltage references for low glitch noise. The employed down-sampling clock signal selects the sampling rate of 200KS/s or 10KS/s with a reduced power depending on applications. The prototype ADC in a 0.18um n-well 1P6M CMOS technology demonstrates the measured DNL and INL within 0.76LSB and 2.47LSB. The ADC shows a maximum SNDR and SFDR of 55dB and 70dB at all sampling frequencies up to 200KS/s, respectively. The active die area is $0.47mm^2$ and the chip consumes 0.94mW at 200KS/s and 0.63mW at 10KS/s at a 1.8V supply.

Design of Deep Learning-based Tourism Recommendation System Based on Perceived Value and Behavior in Intelligent Cloud Environment (지능형 클라우드 환경에서 지각된 가치 및 행동의도를 적용한 딥러닝 기반의 관광추천시스템 설계)

  • Moon, Seok-Jae;Yoo, Kyoung-Mi
    • Journal of the Korean Applied Science and Technology
    • /
    • v.37 no.3
    • /
    • pp.473-483
    • /
    • 2020
  • This paper proposes a tourism recommendation system in intelligent cloud environment using information of tourist behavior applied with perceived value. This proposed system applied tourist information and empirical analysis information that reflected the perceptual value of tourists in their behavior to the tourism recommendation system using wide and deep learning technology. This proposal system was applied to the tourism recommendation system by collecting and analyzing various tourist information that can be collected and analyzing the values that tourists were usually aware of and the intentions of people's behavior. It provides empirical information by analyzing and mapping the association of tourism information, perceived value and behavior to tourism platforms in various fields that have been used. In addition, the tourism recommendation system using wide and deep learning technology, which can achieve both memorization and generalization in one model by learning linear model components and neural only components together, and the method of pipeline operation was presented. As a result of applying wide and deep learning model, the recommendation system presented in this paper showed that the app subscription rate on the visiting page of the tourism-related app store increased by 3.9% compared to the control group, and the other 1% group applied a model using only the same variables and only the deep side of the neural network structure, resulting in a 1% increase in subscription rate compared to the model using only the deep side. In addition, by measuring the area (AUC) below the receiver operating characteristic curve for the dataset, offline AUC was also derived that the wide-and-deep learning model was somewhat higher, but more influential in online traffic.

Design of a Bit-Level Super-Systolic Array (비트 수준 슈퍼 시스톨릭 어레이의 설계)

  • Lee Jae-Jin;Song Gi-Yong
    • Journal of the Institute of Electronics Engineers of Korea SD
    • /
    • v.42 no.12
    • /
    • pp.45-52
    • /
    • 2005
  • A systolic array formed by interconnecting a set of identical data-processing cells in a uniform manner is a combination of an algorithm and a circuit that implements it, and is closely related conceptually to arithmetic pipeline. High-performance computation on a large array of cells has been an important feature of systolic array. To achieve even higher degree of concurrency, it is desirable to make cells of systolic array themselves systolic array as well. The structure of systolic array with its cells consisting of another systolic array is to be called super-systolic array. This paper proposes a scalable bit-level super-systolic amy which can be adopted in the VLSI design including regular interconnection and functional primitives that are typical for a systolic architecture. This architecture is focused on highly regular computational structures that avoids the need for a large number of global interconnection required in general VLSI implementation. A bit-level super-systolic FIR filter is selected as an example of bit-level super-systolic array. The derived bit-level super-systolic FIR filter has been modeled and simulated in RT level using VHDL, then synthesized using Synopsys Design Compiler based on Hynix $0.35{\mu}m$ cell library. Compared conventional word-level systolic array, the newly proposed bit-level super-systolic arrays are efficient when it comes to area and throughput.

LASPI: Hardware friendly LArge-scale stereo matching using Support Point Interpolation (LASPI: 지원점 보간법을 이용한 H/W 구현에 용이한 스테레오 매칭 방법)

  • Park, Sanghyun;Ghimire, Deepak;Kim, Jung-guk;Han, Youngki
    • Journal of KIISE
    • /
    • v.44 no.9
    • /
    • pp.932-945
    • /
    • 2017
  • In this paper, a new hardware and software architecture for a stereo vision processing system including rectification, disparity estimation, and visualization was developed. The developed method, named LArge scale stereo matching method using Support Point Interpolation (LASPI), shows excellence in real-time processing for obtaining dense disparity maps from high quality image regions that contain high density support points. In the real-time processing of high definition (HD) images, LASPI does not degrade the quality level of disparity maps compared to existing stereo-matching methods such as Efficient LArge-scale Stereo matching (ELAS). LASPI has been designed to meet a high frame-rate, accurate distance resolution performance, and a low resource usage even in a limited resource environment. These characteristics enable LASPI to be deployed to safety-critical applications such as an obstacle recognition system and distance detection system for autonomous vehicles. A Field Programmable Gate Array (FPGA) for the LASPI algorithm has been implemented in order to support parallel processing and 4-stage pipelining. From various experiments, it was verified that the developed FPGA system (Xilinx Virtex-7 FPGA, 148.5MHz Clock) is capable of processing 30 HD ($1280{\times}720pixels$) frames per second in real-time while it generates disparity maps that are applicable to real vehicles.

Implementation of RTOS Simulator With Execution Time Estimation (실행시간 추정 가능한 RTOS 시뮬레이터의 구현)

  • 김방현;류성준;김종현;남영광;이광용
    • Proceedings of the Korea Society for Simulation Conference
    • /
    • 2002.05a
    • /
    • pp.125-129
    • /
    • 2002
  • 실시간 운영체제(Real-Time Operating System: 이하 RTOS라 함) 개발환경에서 제공하는 도구 중에 하나인 RTOS 시뮬레이터는 타겟 하드웨어가 호스트에 연결되어 있지 않아도 호스트에서 응용프로그램의 개발과 디버깅을 가능하게 해주는 타겟 시뮬레이션 환경을 제공해 줌으로서, 개발자로 하여금 빠른 시간 내에 응용프로그램을 개발할 수 있도록 지원하며 하드웨어 개발이 완료되기 전에도 응용프로그램을 개발할 수 있게 해 준다. 그러한 이유로 현재 대부분의 상용 RTOS 개발환경에서는 RTOS 시뮬레이터를 제공하고 있다. 그러나 현재 상용 RTOS 시뮬레이터들은 대부분 RTOS의 기능적인 부분들만 호스트에서 동작하도록 구현되어 있어서 RTOS나 RTOS 응용프로그램이 실제 타겟에서 실행될 때의 실질적인 시간 추정이 불가능하다. 이러한 문제점은 실시간 시스템이 정해진 시간 내에 결과를 출력해야 하는 시스템임을 감안한다면 RTOS 시뮬레이터의 가장 큰 결점이 되기 때문에 실행시간 추정 기능을 가지면서 실용화도 가능한 RTOS 시뮬레이터가 필요하다. 본 연구에서는 이러한 문제점을 해결하여 RTOS와 RTOS 응용프로그램이 실제 타겟에서 처리될 때의 실행시간 추정이 가능하고 상용화가 가능한 기계 명령어 기반(machine instruction-based)의 RTOS 시뮬레이터를 연구 개발하였다. 나아가 실행시간의 주요 요소인 파이프라인과 캐쉬의 영향도 고려함으로서 실행시간 추정의 정확도를 향상시켰다 본 연구에서 사용된 RTOS는 한국전자통신연구원(ETRI)에서 2000년에 개발된 Q+이고, Q+가 동작하는 타겟 하드웨어는 ARM 계열의 StrongARM SA-110 마이크로프로세서와 21285 주제어기가 장착된 EBSA-285 보드이다. 측정하면서 수행하였다. 검증 결과 random 상태에서는 문헌자료에 부합되는 예측결과를 보여주었으나, intermediate와 constant 상태에서는 문헌보다 다소 낮은 속도를 보여주었다 이러한 속도차는 추후 현장 데이터를 수집하여 보다 실질적인 검증을 통하여 조정되어야 할 것으로 판단된다.지발광(1.26초)보다 구애발광(1.12초)에서 0.88배 감소하였고, 암컷에서 정지발광(2.99초)보다 구애발광(1.06초)에서 0.35배 감소하였다. 발광양상에서 발광주파수는 수짓의 정지발광에서 0.8 Hz, 수컷 구애발광에서 0.9 Hz, 암컷의 정지발광에서 0.3 Hz, 암컷의 구애발광에서 0.9 Hz로 각각 나타났다. H. papariensis의 발광파장영역은 400 nm에서 700 nm에 이르는 모든 영역에서 확인되었으며 가장 높은 첨두치는 600 nm에 있고 500에서 600 nm 사이의 파장대가 가장 두드러지게 나타났다. 발광양상과 어우러진 교미행동은 Hp system과 같은 결과를 얻었다.하는 방법을 제안한다. 즉 채널 액세스 확률을 각 슬롯에서 예약상태에 있는 음성 단말의 수뿐만 아니라 각 슬롯에서 예약을 하려고 하는 단말의 수에 기초하여 산출하는 방법을 제안하고 이의 성능을 분석하였다. 시뮬레이션에 의해 새로 제안된 채널 허용 확률을 산출하는 방식의 성능을 비교한 결과 기존에 제안된 방법들보다 상당한 성능의 향상을 볼 수 있었다., 인삼이 성장될 때 부분적인 영양상태의 불충분이나 기후 등에 따른 영향을 받을 수 있기 때문에 앞으로 이에 대한 많은 연구가 이루어져야할 것으로 판단된다.태에도 불구하고 [-wh]의미의 겹의문사는 병렬적 관계의 합성어가 아니라 내부구조를 지니지 않은 단순한 단어(minimal $X^{0}$

  • PDF

A Study on Korean Speech Animation Generation Employing Deep Learning (딥러닝을 활용한 한국어 스피치 애니메이션 생성에 관한 고찰)

  • Suk Chan Kang;Dong Ju Kim
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.12 no.10
    • /
    • pp.461-470
    • /
    • 2023
  • While speech animation generation employing deep learning has been actively researched for English, there has been no prior work for Korean. Given the fact, this paper for the very first time employs supervised deep learning to generate Korean speech animation. By doing so, we find out the significant effect of deep learning being able to make speech animation research come down to speech recognition research which is the predominating technique. Also, we study the way to make best use of the effect for Korean speech animation generation. The effect can contribute to efficiently and efficaciously revitalizing the recently inactive Korean speech animation research, by clarifying the top priority research target. This paper performs this process: (i) it chooses blendshape animation technique, (ii) implements the deep-learning model in the master-servant pipeline of the automatic speech recognition (ASR) module and the facial action coding (FAC) module, (iii) makes Korean speech facial motion capture dataset, (iv) prepares two comparison deep learning models (one model adopts the English ASR module, the other model adopts the Korean ASR module, however both models adopt the same basic structure for their FAC modules), and (v) train the FAC modules of both models dependently on their ASR modules. The user study demonstrates that the model which adopts the Korean ASR module and dependently trains its FAC module (getting 4.2/5.0 points) generates decisively much more natural Korean speech animations than the model which adopts the English ASR module and dependently trains its FAC module (getting 2.7/5.0 points). The result confirms the aforementioned effect showing that the quality of the Korean speech animation comes down to the accuracy of Korean ASR.