Function-Guided Energy-Precision Optimization with Precision-Rate-Complexity Bivariate Models

  • Hao Liu
  • Rong HuangEmail author
  • Zhihai He
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11258)


In an intelligent wireless vision sensor network, an intra encoder is used for the energy-precision optimization with two control parameters: sampling ratio and quantization parameter, which have a direct impact on the coding bit rate, encoder complexity, wireless transmission energy, as well as the server-end object classification precision. Through extensive experiments, we construct the precision-rate-complexity bivariate models to understand the behaviors of the intra encoder and the deep convolutional neural networks, and then characterize the inherent relationship between bit rate, encoding complexity, classification precision and these two control parameters. With these models, we study the problem of optimization control of the wireless vision sensor node so that the node-end energy can be minimized subject to the server-end object classification precision. Our experimental results demonstrate that the proposed control method is able to effectively adjust the energy consumption of the sensor node while achieving the target classification performance.


Intra encoder Energy-precision optimization Bivariate models Deep convolutional neural networks 



This work is supported by the Natural Science Foundation of Shanghai (18ZR1400300).


  1. 1.
    Pastuszak, G., Abramowski, A.: Algorithm and architecture design of the H.265/HEVC intra encoder. IEEE Trans. Circuits Syst. Video Technol. 26(1), 210–222 (2016)CrossRefGoogle Scholar
  2. 2.
    Li, X., Wien, M., Ohm, J.R.: Rate-complexity-distortion optimization for hybrid video coding. IEEE Trans. Circuits Syst. Video Technol. 21(7), 957–970 (2011)CrossRefGoogle Scholar
  3. 3.
    Chuah, S.P., Tan, Y.P., Chen, Z.: Rate and power allocation for joint coding and transmission in wireless video chat applications. IEEE Trans. Multimed. 17(5), 687–699 (2015)CrossRefGoogle Scholar
  4. 4.
    Chen, Z., Tsaftaris, S.A., Soyak, E., Katsaggelos, A.K.: Application-aware approach to compression and transmission of H.264 encoded video for automated and centralized transportation surveillance. IEEE Trans. Intell. Transp. Syst. 14(4), 2002–2007 (2013)CrossRefGoogle Scholar
  5. 5.
    Chao, J., Huitl, R., Steinbach, E., Schroeder, D.: A novel rate control framework for SIFT/SURF feature preservation in H.264/AVC video compression. IEEE Trans. Circuits Syst. Video Technol. 25(6), 958–972 (2015)CrossRefGoogle Scholar
  6. 6.
    Ko, J.H., Mudassar, B.A., Mukhopadhyay, S.: An energy-efficient wireless video sensor node for moving object surveillance. IEEE Trans. Multi-Scale Comput. Syst. 1(1), 7–18 (2015)CrossRefGoogle Scholar
  7. 7.
    Minervini, M., Tsaftaris, S.A.: Classification-aware distortion metric for HEVC intra coding. In: Proceedings of IEEE Visual Communications and Image Processing, Singapore, pp. 1–4 (2015)Google Scholar
  8. 8.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), Lake Tahoe, NV, pp. 1097–1105 (2012)Google Scholar
  9. 9.
    Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)
  10. 10.
    Redondi, A., Baroffio, L., Bianchi, L., Cesana, M., Tagliasacchi, M.: Compress-then-analyze versus analyze-then-compress: what is best in visual sensor networks? IEEE Trans. Mob. Comput. 15(12), 3000–3013 (2016)CrossRefGoogle Scholar
  11. 11.
  12. 12.
    HEVC Software Repository — HM-16.7 Reference Model.

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.College of Information Science and TechnologyDonghua UniversityShanghaiChina
  2. 2.Department of Electrical and Computer EngineeringUniversity of MissouriColumbiaUSA

Personalised recommendations