The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

Modeling and Classification of MPEG VBR Video Data using Gradient-based Fuzzy c_means with Divergence Measure

분산 기반의 Gradient Based Fuzzy c-means 에 의한 MPEG VBR 비디오 데이터의 모델링과 분류

  • 박동철 (명지대학교 정보공학과 지능컴퓨팅 연구실) ;
  • 김봉주 (명지대학교 정보공학과 지능컴퓨팅 연구실)
  • Published : 2004.07.01
Download PDF
⟨ Previous Next ⟩

Abstract

GBFCM(DM), Gradient-based Fuzzy c-means with Divergence Measure, for efficient clustering of GPDF(Gaussian Probability Density Function) in MPEG VBR video data modeling is proposed in this paper. The proposed GBFCM(DM) is based on GBFCM( Gradient-based Fuzzy c-means) with the Divergence for its distance measure. In this paper, sets of real-time MPEG VBR Video traffic data are considered. Each of 12 frames MPEG VBR Video data are first transformed to 12-dimensional data for modeling and the transformed 12-dimensional data are Pass through the proposed GBFCM(DM) for classification. The GBFCM(DM) is compared with conventional FCM and GBFCM algorithms. The results show that the GBFCM(DM) gives 5∼15% improvement in False Alarm Rate over conventional algorithms such as FCM and GBFCM.

GPDF(Gaussian Probability Density Function)을 효율적으로 군집화할 수 있는 GBFCM(DM)(Gradient Based Fuzzy c_means with Divergence Measure) 알고리즘이 본 논문에서 제안되었다. 제안된 GBFCM(DM)은 데이터 사이의 거리 척도로 발산거리(Divergence measure)를 적용한 새로운 형태의 FCM으로, 기존의 GBFCM에 기반을 두는 알고리즘이다. 본 논문에서는 MPEG VBR 비디오 데이터를 GPDF형태의 다차원 데이터로 변형시켜 모델링 하고, 모델링 한 MPEG VBR 비디오 데이터를 영화 또는 스포츠 형태로 분류하는데 응용되었다. 본 논문의 실험에서 기존의 FCM, GBFCM과 새롭게 제안된 GBFCM(DM)을 사용하여 모델링 및 분류결과를 상호 비교하였다. 비교결과 GBFCM(DM)이 오분류율의 기준에서 기존의 다른 알고리즘들에 비해 약 5∼l5%의 향상된 성능을 보였다.

Keywords

References

  1. IEEE J. Select. Areas Comm. v.15 Guest editorial real-time video services in multimedia networks G. Pacifici(et al.) https://doi.org/10.1109/JSAC.1997.611152
  2. IEEE Tr. Fuzzy Syst. v.6 Fuzzy-based rate control for real-time MPEG video D. Tsang(et al) https://doi.org/10.1109/91.728442
  3. ACM Trans. Inform. Sust. v.13 no.4 Motion recovery for video content classification N. Dimitrova;F. Golshani https://doi.org/10.1145/211430.211433
  4. Pattern Recog. v.30 no.4 Video shot detection and characterization for video databases N. Patel;I. Sethi https://doi.org/10.1016/S0031-3203(96)00114-8
  5. IEEE Tr. Fuzzy Syst v.9 no.1 MPEG VBR Video Traffic Modeling and Classification Using Fuzzy Technique Q. Liang;J. Mendel https://doi.org/10.1109/91.917124
  6. Pattern Recognition Using Neural Networks Carl Looney
  7. Univ. Wurzberg. Inst. Comp. Sci., Rep. 101 Statistical properties of MPEG video traffic and their impact on traffic modeling in ATM systems O. Rose
  8. IEEE Trans. Networking v.7 Workload models of VBR video traffic and their use in resource allocation policies P. Manzoni(et al.) https://doi.org/10.1109/90.779207
  9. Proc. INFOCOM'95 v.2 Statistical characteristics and multiplexing of MPEG streams M. Krunz(et al.)
  10. Pattern recognition with fuzzy objective function algorithms J. Bezdek
  11. IEEE Tr. on PAMI v.24 Information Theoretic Clustering E. Gokcay;J. C Principe https://doi.org/10.1109/34.982897
  12. IEEE Tr. Neural Networks,(in review) Centroid Neural Network with the Divergence Measure for GPDF Data Clustering D. Park;O. Kwon
  13. IEE Electronic Letters v.49 no.4 Clustering of Gaussian Probability Density Functions Using Centroid Neural Networks D. Park(et al.)