Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Improvement of Distributed Compressive Video Sensing Using Reliability Estimation

신뢰성 예측을 이용한 분산 압축 비디오 센싱의 성능 개선

  • 김진수 (한밭대학교 정보통신공학과)
  • Received : 2018.10.03
  • Accepted : 2018.10.31
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, remote sensing video applications have become increasingly important in many wireless networks. Distributed compressive video sensing (DCVS) framework in these applications has been studied to reduce encoding complexity and to simultaneously capture and compress video data. Specially, a motion compensated block compressed sensing with smoothed projected Landweber (MC-BCS-SPL) has been actively researched for one useful algorithm of DCVS schemes, However, conventional MC-BCS-SPL schemes do not provide good visual qualities in reconstructed Wyner-Ziv (WZ) frames. In this paper, the conventional schemes of MC-BCS-SPL are described and then upgraded to provide better visual qualities in WZ frames by introducing reliability estimate between adjacent key frames and by constructing efficiently motion-compensated interpolated frames. Through experimental results, it is shown that the proposed algorithm is effective in providing better visual qualities than conventional algorithm.

최근에 원거리 비디오 센싱과 같은 응용은 많은 무선 네트워크에 중요한 응용으로 크게 관심을 받고 있다. 분산 압축 비디오 센싱기술은 높은 부호화 복잡도를 간단히 하고, 동시에 비디오 데이터를 캡처함과 동시에 압축함으로써 이 분야에 적용 가능한 기술로 고려되고 있다. 특히, 움직임 보상 블록 압축센싱 기술인 MC-BCS-SPL은 분산 압축 비디오 센싱 방법 중에 효과적인 기술로서 고려되고 있으나, 복원된 위너-지브 프레임에서 우수하지 못한 성능을 제공한다. 본 논문에서는 기존의 MC-BCS-SPL 알고리즘을 살펴보고, 이웃하는 키프레임 사이에 신뢰성에 기초하여 효과적으로 움직임 보상 프레임을 얻는 방법을 도입함으로써 우수한 화질을 제공하는 방법을 제안한다. 다양한 실험 결과를 통하여 제안한 알고리즘은 기존의 알고리즘에 비해 우수한 화질을 제공할 수 있음을 확인한다.

Keywords

SOJBB3_2018_v23n6_47_f0001.png 이미지

Fig. 1 MC-BCS-SPL Structure[2]

SOJBB3_2018_v23n6_47_f0002.png 이미지

Fig. 2 Formulation of Pseudo-Code in BCS-SPL and MC-BCS-SPL (a) BCS-SPL[2] (b) MC-BCS-SPL[3]

SOJBB3_2018_v23n6_47_f0003.png 이미지

Fig. 3 Pseudo-Code for RMSE-Based Reconstruction[8]. (a) RMSE-Based MC-BC-SPL Algorithm (b) Residual Reconstruction

SOJBB3_2018_v23n6_47_f0004.png 이미지

Fig. 4 Pseudo-Code for Correlation-Based Reconstruction[9] (a) Correlation-Based MC-BC-SPL Algorithm (b) Residual Reconstruction

SOJBB3_2018_v23n6_47_f0005.png 이미지

Fig. 5 Proposed MC-BCS-SPL algorithm (a) the proposed MC-BCS-SPL algorithm and (b) the part of pixel-domain reconstruction

SOJBB3_2018_v23n6_47_f0006.png 이미지

Fig. 6 Bilateral Motion Estimation (a) Initial forward Motion Estimation and (b) the Bilateral Motion Estimation

SOJBB3_2018_v23n6_47_f0007.png 이미지

Fig. 7 PSNR Performance Comparison between the Proposed Algorithm and the Conventional Algorithms (a) Foreman (b) Susie (c) Football

SOJBB3_2018_v23n6_47_f0008.png 이미지

Fig. 8 RD Performances Comparison (a) Foreman (b) Susie

References

  1. Donoho, D. L., "Compressed Sensing," IEEE Transactions on Information Theory, Vol. 52, No. 4, pp. 1289-1306, Apr. 2006. https://doi.org/10.1109/TIT.2006.871582
  2. Mun, S. and Fowler, J. E., "Block Compressed Sensing of Images Using Directional Transforms," in Proceedings of IEEE International Conference on Image Processing, USA, pp. 3021-3024, 2009.
  3. Mun, S. and Flower, J. E., "Residual Reconstruction for Block-based Compressed Sensing of Video," in Proceedings of Data Compression Conference, pp. 183-192, 2011.
  4. Gan, L., "Block Compressed Sensing of Natural Images," Proceedings of the International Conference on Digital Signal Processing, Cardiff, UK, pp. 403-406, 2007.
  5. Ryu, J., and Kim, "An Effective MC-BCS-SPL Algorithm and Its Performance Comparison with Respect to Prediction Structuring Method," Journal of the Korea Institute of Information and Communication Engineering (JKIICE), Vol. 21, No. 7, pp. 1355-1363, 2017. https://doi.org/10.6109/JKIICE.2017.21.7.1355
  6. Nguyen, Q. H., Dinh, K. Q., Nguyen, V. A., Trinh, C. V., Park, Y., and Jeon. B., "A Skip-mode Coding for Distributed Compressive Video Sensing," Journal of Broadcast Engineering, Vol. 19, No. 2. pp 257-267, March. 2014. https://doi.org/10.5909/JBE.2014.19.2.257
  7. Fowler, J. E., Mun, S., and Tramel, E. W., "Multiscale Block Compressed Sensing with Smoothed Projected Landweber Reconstruction," in Proceedings of 19th European Signal Processing Conference, Aug 2011, pp. 564-568.
  8. Ryu, J., and Kim, J., "Performance Comparison of BCS-SPL Techniques Against a Variety of Restoring Block Sizes," Journal of the Korea Industrial Information System Society, Vol. 21, No. 1, pp. 21-28, 2016.
  9. Ryu, J., and Kim, J., "A Stabilization of MC-BCS-SPL Scheme for Distributed Compressed Video Sensing," Journal of Korea Multimedia Society, Vol. 20, No. 5, pp. 731-739, 2017. https://doi.org/10.9717/kmms.2017.20.5.731
  10. Che, W., Gao, X., Fan, X., Jinang, F., and Zhao, D., "Spatial-temporal Recovery for Hierarchical Frame Based Video Compressed Sensing," 2015 IEEE International Conference on Image Processing (ICIP), 2015.
  11. Sukumaran, A. N., Sankararajan, R,. and Rajendiran, K., "Video Compressed Sensing Framework for Wireless Multimedia Sensor Networks using a Combination of Multiple Matrices," Computers & Electrical Engineering, Vol. 44, pp. 51-66, 2015. https://doi.org/10.1016/j.compeleceng.2015.02.008
  12. Rehman, A., Shah, G., and Tahir, M., "Compressed Sensing based Adaptive Video Coding for Resource Constrained Devices," 2016 International Wireless Communications and Mobile Computing Conference (IWCMC), 2016.
  13. Ebrahim, M., and Chia, W., "Block Compressive Sensing Based Multi-phase Reconstruction (MPR) Framework for Video," Advances in Machine Learning and Signal Processing, pp. 105-115, 2016.
  14. Unde, A. S., and Deepthi, P., "Block Compressive Sensing: Individual and Joint Reconstruction of Correlated Images," Journal of Visual Communication and Image Representation, Vol. 44, pp. 187-197, 2017. https://doi.org/10.1016/j.jvcir.2017.01.028
  15. Park, S., Choi, J., Kim, C., Lee, S., and Kang, J., "Efficient Distributed Video Coding Using Symmetric Motion Estimation and Channel Division," PACRIM09, 2009.
  16. Kim, J., and Lee, B., "Wave Information Retrieval Algorithm Based on Iterative Refinement," Journal of the Korea Industrial Information System Society, Vol. 21, No. 1, pp. 7-15, 2016.
  17. Ryu, J., and Kim, J., "Reconstructed ImageQuality Improvement of Distributed Compressive Video Sensing Using Temporal Correlation," Journal of the Korea Industrial Information System Society, Vol. 22, No. 2, pp. 27-34, 2017. https://doi.org/10.9723/jksiis.2017.22.2.027