• Title/Summary/Keyword: 코드북 모델

Search Result 33, Processing Time 0.018 seconds

Codebook-Based Foreground-Background Segmentation with Background Model Updating (배경 모델 갱신을 통한 코드북 기반의 전배경 분할)

  • Jung, Jae-young
    • Journal of Digital Contents Society
    • /
    • v.17 no.5
    • /
    • pp.375-381
    • /
    • 2016
  • Recently, a foreground-background segmentation using codebook model has been researched actively. The codebook is created one for each pixel in the image. The codewords are vector-quantized representative values of same positional training samples from the input image sequences. The training is necessary for a long time in the most of codebook-based algorithms. In this paper, the initial codebook model is generated simply using median operation with several image frames. The initial codebook is updated to adapt the dynamic changes of backgrounds based on the frequencies of codewords that matched to input pixel during the detection process. We implemented the proposed algorithm in the environment of visual c++ with opencv 3.0, and tested to some of the public video sequences from PETS2009. The test sequences contain the various scenarios including quasi-periodic motion images, loitering objects in the local area for a short time, etc. The experimental results show that the proposed algorithm has good performance compared to the GMM algorithm and standard codebook algorithm.

Speaker Adaptation in VQ and HMM Based Speech Recognition (VQ와 HMM을 이용한 음성인식에서 화자적응에 관한 연구)

  • 이대룡
    • Proceedings of the Acoustical Society of Korea Conference
    • /
    • 1991.06a
    • /
    • pp.54-57
    • /
    • 1991
  • 본 논무에서는 HMM과 VQ를 이용한 고립단어에 대한 화자종속 및 화자독립 음성인식시스템을 만들고 여기에 화자적응을 하는 방법에 대한 연구를 했다. 화자적응방법에는 크게 VQ코드북을 적응시키는 방법과 HMM패러미터블 적응시키는 방법이 있다. 코드북적응을 하는 방법으로서 기존코드북에 대해 새로운화자의 적응음성을 양자화한 뒤 각 코드벡터에 해당하는 적응음성의 평균을 구해서 새로운 화자의 코드북을 구해주는 방법과 기준코드북에 대해 새로운화자의 적응음성을 양자화할 때 HMM의 각 상태에서 각각의 코드벡터를 발생할 확률을 거리오차의 계산에서 고려해 비록 거리오차는 크지만 그 코드벡터를 발생할 확률이 매우 높으면 적응음성이 그 코드벡터에 index되게해서 각 코드벡터에 해당하는 모든 적응음성데이타의 평균을 새로운 코드북으로 하는 두가지 알고리즘을 제안한다. 이렇게 함으로써 기존의 기준코드북을 초기 코드북으로해서 LBG알고리즘을 사용해서 적응음성데이타에 대한 새로운 코드북을 만드는 방법에 비해 5-10배의 계산시간을 감소하게 된다. 이 새로운 코드북으로 적응음성데이타를 다시 index해서 이 index된 음성렬로 HMM패러미터를 적응했다. 제안된 알고리즘이 코드북적응을 하는 경우에 기존의 적응방법에 비해 5-10배의 계산 시간을 단축하면서 인식률에서는 더 나은결과를 얻었다. 또 같은 적응방법에 대해서 화자종속모델 보다는 화자독립모델에 대해서 화자적응하는 것이 더 나은 인식결과를 보여주었다.

  • PDF

A Comparative Study on Parameter for Korean Phoneme-based HMM Model Decision (한국어 음소 HMM 모델 결정을 위한 파라미터 비교 연구)

  • 권혁제
    • Proceedings of the Acoustical Society of Korea Conference
    • /
    • 1998.08a
    • /
    • pp.302-305
    • /
    • 1998
  • 음소의 확률적 분포를 이용하는 음소 HMM 모델을 결정하기 위한 여러 가지 거리 측정방법에 대한 연구이다. 음소 HMM 모델 결정을 위해서 LPC 계수를 이용하고, 거리 측정자를 LPC 계수, LPC 스첵트럼, LPC 켑스트럼 등의 파라미터를 이용하고, 또한 양자화 과정은 k-means 와 LBG 알고리즘을 혼합한 하이브리드 알고리듬을 사용하였다. LPC 코드북을 구성하기 위해 세 가지 파라미터를 유클리디안 거리로 거리측정에 이용하였다. 이렇게 양자화한 파라미터의 평균과 분산을 구하고, 양자화한 파라미터 코드북의 확률갑승ㄹ 비교해 한국어 음소 HMM 모델 결정을 위한 거리 측정 파라미터를 비교하였으며, 그 결과 LPC 계수를 주파수 영역으로 변환하여 유클리디안 거리를 이용한 코드북의 분산이 작으므로 상대적으로 높은 확률을 가짐을 보았다.

  • PDF

Determination and Performance Evaluation of a Codebook for MIMO Systems Utilizing Statistical Properties of The Spatial Channel Model (공간 채널 모델의 통계적 특성을 활용하는 MIMO 시스템의 코드북 결정 및 성능 평가)

  • Suh, Junyeub;Kang, Hosik;Sung, Wonjin
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.52 no.7
    • /
    • pp.22-30
    • /
    • 2015
  • For long-term evolution (LTE) MIMO transmission, codebooks are used to utilize the estimated channel information under the limited feedeback environment, and related study has been actively performed. Existing codebooks include codevectos constructed based on vector quantization (VQ) and discrete Fourier transform (DFT), and the LTE standard specifies codebooks modified from these examples to support up to 8 transmit antennas. As the number of antennas increases and as the spatial channel model is used as a standard environment to evaluate the LTE transmission performance, new beamforming methods as well as codebook designs are needed. In this paper, we implement the 3-dimensional spatial channel model (3D-SCM) to analyze the key statistical characteristics of the generated channel, and present efficient ways of determining corresponding codebooks. In particular, we propose a nonuniform-phase DFT-based codebook to improve the existing uniform-phase DFT-based codebook, and evaluate its performance under the given SCM transmission environment. There exists a strong tendancy in statistical distributions of the phase difference between adjacent antenna elements for the SCM, which can be appropriately exploited in codebook design to produce a performance gain over the existing design.

Online VQ Codebook Generation using a Triangle Inequality (삼각 부등식을 이용한 온라인 VQ 코드북 생성 방법)

  • Lee, Hyunjin
    • Journal of Digital Contents Society
    • /
    • v.16 no.3
    • /
    • pp.373-379
    • /
    • 2015
  • In this paper, we propose an online VQ Codebook generation method for updating an existing VQ Codebook in real-time and adding to an existing cluster with newly created text data which are news paper, web pages, blogs, tweets and IoT data like sensor, machine. Without degrading the performance of the batch VQ Codebook to the existing data, it was able to take advantage of the newly added data by using a triangle inequality which modifying the VQ Codebook progressively show a high degree of accuracy and speed. The result of applying to test data showed that the performance is similar to the batch method.

Codebook-Based Foreground Extraction Algorithm with Continuous Learning of Background (연속적인 배경 모델 학습을 이용한 코드북 기반의 전경 추출 알고리즘)

  • Jung, Jae-Young
    • Journal of Digital Contents Society
    • /
    • v.15 no.4
    • /
    • pp.449-455
    • /
    • 2014
  • Detection of moving objects is a fundamental task in most of the computer vision applications, such as video surveillance, activity recognition and human motion analysis. This is a difficult task due to many challenges in realistic scenarios which include irregular motion in background, illumination changes, objects cast shadows, changes in scene geometry and noise, etc. In this paper, we propose an foreground extraction algorithm based on codebook, a database of information about background pixel obtained from input image sequence. Initially, we suppose a first frame as a background image and calculate difference between next input image and it to detect moving objects. The resulting difference image may contain noises as well as pure moving objects. Second, we investigate a codebook with color and brightness of a foreground pixel in the difference image. If it is matched, it is decided as a fault detected pixel and deleted from foreground. Finally, a background image is updated to process next input frame iteratively. Some pixels are estimated by input image if they are detected as background pixels. The others are duplicated from the previous background image. We apply out algorithm to PETS2009 data and compare the results with those of GMM and standard codebook algorithms.

Analysis of Phoneme/Isolated Word Recognition Rate Using Codebook and VQ Optimization (코드북과 VQ 최적화에 의한 음소/고립단어 인식률 분석)

  • Ahn, Hong-Jin;Joo, Sang-Hyun;Chin, Won;Kim, Ki-Doo
    • Proceedings of the IEEK Conference
    • /
    • 1999.06a
    • /
    • pp.675-678
    • /
    • 1999
  • 본 논문에서는 음소별 코드북 개수의 선택과 벡터 양자화에 따른 음소 인식률과 고립단어 인식률에 대하여 다룬다. 음성모델은 이산 확률 밀도를 갖는 DHMM(Discrete Hidden Markov Model)을 사용하였으며, 코드북 생성과 벡터 양자화 알고리즘으로는 K-means 알고리즘과 LBG(Linde, Buzo, Gray) 알고리즘을 사용하였다 음소별 코드북 개수와 벡터 양자화를 최적화함으로써 음소 인식률을 향상시킬 수 있으며, 그 결과 안정된 고립단어 인식률을 얻을 수 있다.

  • PDF

Isolated Korean Digits Recognition Using Stochasitc Transition Models With Phoneme-based VQ Codebooks (음소단위 코드북간의 확률적 전이 모델을 이용한 한국어 숫자음 인식에 관한 연구)

  • Choi, Hwan-Jin;Oh, Yung-Hwan
    • Annual Conference on Human and Language Technology
    • /
    • 1993.10a
    • /
    • pp.149-157
    • /
    • 1993
  • 음성인식을 위해 다양한 방법들이 제안되어 있다. 본 연구에서는 음소단위 각각의 벡터 양자화된 코드북의 색인을 학습하는 HMM을 이용하여 한국어 숫자음을 대상으로 인식 실험을 수행하였다. 실험결과, 기존의 단어단위 HMM과 음소단위로 이루어진 유한상태기계(FSM)구조의 인식기에 비해 높은 인식율을 보였다.

  • PDF

Performance Analysis of Precoded LTE-Advanced Uplink System (LTE-Advanced 시스템의 선부호화된 상향 링크 성능 분석)

  • Kim, Sang-Gu;Li, Xun;Kim, Young-Ju
    • Journal of the Institute of Electronics Engineers of Korea TC
    • /
    • v.48 no.5
    • /
    • pp.8-15
    • /
    • 2011
  • LTE-Advanced aims at peak data rates of 1Gbits/s for the downlink and 500 Mbits/s for the uplink, which can be accomplished only by using wide spectrum allocation of 100MHz as well as advanced multiple input multiple output antenna techniques to the uplink. This paper analyzes the uplink precoding techniques which include LTE codebook of downlink, singular value decomposition codebook, and equal gain transmission codebook over LTE defined single carrier frequency division multiplexing systems. Finally considering nonlinear transmit power amplifier model, it is shown that link-level performance of EGT is superior to those of any other precoding schemes.

Design and Performance Gain Evaluation of a Multi-Rank Codebook Utilizing Statistical Properties of the Spatial Channel Model (공간 채널 모델의 통계적 특성을 반영한 다중 랭크 코드북의 설계 및 성능 이득 평가)

  • Kim, Changhyeon;Sung, Wonjin
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.41 no.7
    • /
    • pp.723-731
    • /
    • 2016
  • A core technological base to provide enhanced data rates required by 5G mobile wireless communications is the improved bandwidth efficiency using massive multiple-input multiple-output (MIMO) transmission. MIMO transmission requires the channel estimation using the channel state information reference signaling (CSI-RS) and appropriate beamforming, thus the design of the codebook defining proper beamforming vectors is an important issue. In this paper, we propose a multi-rank codebook based on the discrete Fourier transform (DFT) matrix, by utilizing statistical properties of the channel generated by the spatial channel model (SCM). The proposed method includes a structural change of the precoding matrix indicator (PMI) by considering the phase difference distributions between adjacent antenna elements, as well as the selected codevector characteristics of each transmission layer. Performance gain of the proposed method is evaluated and verified by making the performance comparison to the 3GPP standard codebooks adopted by Long-Term Evolution (LTE) systems.