Low-Power Face Detection for Smart Camera

Part of the KAIST Research Series book series (KAISTRS)


Recently the development of intelligent surveillance system increasingly requires low power consumption. For power saving, this chapter presents an event detection function based on automatically detected human faces, which adaptively changes from low-power camera mode to high performance camera mode. We propose efficient face detection (FD) method being operated under the low-power camera mode. By employing two-stage structure (i.e., region-of-interest (ROI) selection and false positive (FP) reduction), the proposed FD method requires very low computational complexity and memory requirements without sacrificing the face detection robustness. Experimental results demonstrated that the proposed FD could be implemented in low-power video cameras with promising performance.


Face detection Intelligent surveillance system Low power hardware architecture Event detection Smart camera Two-stage structure 



This work is supported by the Center for Integrated Smart Sensors funded by the Ministry of Science, ICT & Future Planning as Global Frontier Project.


  1. 1.
    Bramberger M, Doblander A, Maier A, Rinner B, Schwaback H (2006) Distributed embedded smart cameras for surveillance applications. IEEE Comput Mag 39(2):68–75CrossRefGoogle Scholar
  2. 2.
    Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behaviors. IEEE Trans Syst Man Cybern Part C Appl Rev 34(3):334–352Google Scholar
  3. 3.
    Kim G, Kim J, Jung J, Kyung C. –M. (2012) Energy-aware operation of black box surveillance cameras under event uncertainty and memory constraint. In: IEEE international conference multimedia and Expo (ICME), pp 782–787Google Scholar
  4. 4.
    Irgan K, Ünsalan C, Baydere S (2014) Low-cost prioritization of image blocks in wireless sensor networks for border surveillance. J Netw Comput Appl 38:54–64CrossRefGoogle Scholar
  5. 5.
    Huang C, Ai H, Li Y, Lao S (2007) High-performance rotation invariant multiview face detection. IEEE Trans Pattern Anal Mach Intell 29(4):671–686Google Scholar
  6. 6.
    Osuna E, Freund R, Girosi F (1997) Training support vector machines: an application to face detection. In: IEEE computer society conference computer vision and pattern recognition (CVPR), pp 130–136Google Scholar
  7. 7.
    Li Y, Gong S, Liddell H (2000) Support vector regression and classification based multi-view face detection and recognition. In: IEEE international conference automatic face and gesture recognition (FG), pp 300–305Google Scholar
  8. 8.
    Viola P, Jones MJ (2004) Robust real-time face detection. Int J Comput Vision 57(2):137–154CrossRefGoogle Scholar
  9. 9.
    Jang J–S, Kim J–H (2008) Fast and robust face detection using evolutionary pruning. IEEE Trans Evol Comput 12(5):562–571Google Scholar
  10. 10.
    Wu B, Ai H, Huang C, Lao S (2004) Fast rotation invariant multi-view face detection based on real AdaBoost. In: IEEE international conference automatic face and gesture recognition (FG), pp 79–84Google Scholar
  11. 11.
    Vapnik VN (1998) Statistical Learning Theory. WileyGoogle Scholar
  12. 12.
    Tabatabaie ZS, Rahmat RW, Udzir NIB, Kheirkhah E (2009) A hybrid face detection system using combination of appearance-based and feature-based methods. Int J Comput Sci Network Secur 9(5):181–185Google Scholar
  13. 13.
    Kim B, Ban S–W, Lee M (2008) Improving AdaBoost based face detection using face-color preferable selective attention. Intell Data Eng Autom Learn LNCS5326:88–95Google Scholar
  14. 14.
    Zhang C, Zhang Z (2010) A survey on recent advances in face detection. Technical report, MSR-TR-2010–66, Microsoft ResearchGoogle Scholar
  15. 15.
    Li S, Zhu L, Zhang Z, Blake A, Zhang H, Shum H (2002) Statistical learning of multi-view face detection. In: European conference computer vision (ECCV), pp 67–81Google Scholar
  16. 16.
    Wei Y, Bing X, Chareonsak C (2004) FPGA implementation of AdaBoost algorithm for detection of face biometrics. In: IEEE international workshop on biomedical circuits and systems, pp S1–6Google Scholar
  17. 17.
    Zou WWW, Yuen PC (2012) Very low resolution face recognition problem. IEEE Trans Image Proc 21(1):327–340MathSciNetCrossRefGoogle Scholar
  18. 18.
    He T, Krishnamurthy S, Stankovic JA, Abdelzaher T, Luo L, Stoleru R, Yan T, Gu L (2004) Energy-efficient surveillance system using wireless sensor networks. In: ACM international conference mobile systems, applications, and services, pp 270–283Google Scholar
  19. 19.
    Coumeri SL, Thomas DE (2000) Memory modeling for system synthesis. IEEE Trans Very Large Scale Integr (VLSI) Syst 8(3):327–334Google Scholar
  20. 20.
  21. 21.
    Tan X, Chen S, Zhou Z-H, Zhang F (2006) Face recognition from a single image per person: a survey. Pattern Recogn 39(9):1725–1745CrossRefGoogle Scholar
  22. 22.
    Kim H–I, Lee SH, Moon JI, Park H–S, Ro YM (2014) Face detection for low power event detection in intelligent surveillance system. In: IEEE international conference digital signal processing (DSP), pp 562–567Google Scholar
  23. 23.
    Chan CH, Kittler J (2010) Sparse representation of (multiscale) histograms for face recognition robust to registration and illumination problems. In: IEEE international conference image processing (ICIP), pp 2441–2444Google Scholar
  24. 24.
    Ahonen T, Hadid A, Pietikäinen M (2006) Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28(12):2037–2041Google Scholar
  25. 25.
    Zhu C, Bichot C, Chen L (2011) Color orthogonal local binary patterns combination for image region description. Rapport technique RR-LIRIS-2011-012, LIRIS UMR, 5205, 15Google Scholar
  26. 26.
    Fauvel M, Chanussot J, Benediktsson JA (2006) Evaluation of kernels for multiclass classification of hyperspectral remote sensing data. In: IEEE international conference acoustics, speech, and signal processing (ICASSP)Google Scholar
  27. 27.
    Chang C–C, Lin C–J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):article 27Google Scholar
  28. 28.
    Phillips PJ, Moon H, Rizvi SA, Rauss PJ (2000) The FERET evaluation methodology for face-recognition algorithms. IEEE Trans Pattern Anal Mach Intell 22(10):1090–1104Google Scholar
  29. 29.
  30. 30.
  31. 31.
  32. 32.
    Hori Y, Kuroda T (2007) A 0.79-mm2 29-mW real-time face detection core. IEEE J Solid-State Circuits 42(4):790–797CrossRefGoogle Scholar
  33. 33.
    Nguyen D, Halupka D, Aarabi P, Sheikholeslami A (2006) Real-time face detection and lip feature extraction using field-programmable gate arrays. IEEE Trans Syst Man Cybern Part B Cybern 36(4):902–912CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2016

Authors and Affiliations

  1. 1.School of Electrical EngineeringKAISTKaistRepublic of Korea

Personalised recommendations