An Ultra-Low-Power Image Signal Processor for Smart Camera Applications

Part of the KAIST Research Series book series (KAISTRS)


Among thriving cyber physical systems (CPS), smart camera applications require to run both image sensors and image signal processors (ISPs) to capture images whenever necessary. Due to the nature of such applications (i.e., constantly capturing images and analyzing the images to detect any event of interest), the image sensor and ISP become the two most energy consuming components in smart camera applications. In this chapter, we start with our intuition that the perceptive quality of images is not strongly correlated with the accuracy of object detection algorithms and propose three techniques that require only minor modifications to the baseline ISP but dramatically reduce the ISP energy consumption in object detection mode for smart camera applications. When joining three proposed techniques, we demonstrate that our ISP consumes only 3 % of the baseline ISP energy while degrading face detection accuracy by 3–4 %.


Image signal processor Smart camera Face detection 



This work is supported by the Center for Integrated Smart Sensors funded by the Ministry of Science, ICT & Future Planning as the Global Frontier Project and an NSF grant (CCF-0953603).


  1. 1.
    BYD Microelectronics Co., Ltd., QVGA CMOS Image Sensor BF3901 DatasheetGoogle Scholar
  2. 2.
    DDC PowerShrink™ Platform.
  3. 3.
    Buchsbaum G (1980) A spatial processor model for object colour perception. J Franklin Inst 310(1)Google Scholar
  4. 4.
    Bayer BE (1976) Color imaging array. USA Patent US3971065 (A), 20 July 1976Google Scholar
  5. 5.
    Parameter values for the HDTV standards for production and international programme exchange.
  6. 6.
    Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: EEE computer society conference on computer vision and pattern recognitionGoogle Scholar
  7. 7.
    Inside the Canon RAW Format Version 2.
  8. 8.
    OpenCV Library.
  9. 9.
    Tutorial on OpenCV HaarTraining.
  10. 10.
    Wang Z, Bovik A, Sheikh H, Simoncelli E (2004) Image quality assessment: from error visibility to structural aimilarity. IEEE Trans Image Proc 13(4)Google Scholar
  11. 11.
    LiKamWa R (2014) Extended abstract: efficient image processing for continuous mobile vision. ACM PhD ForumGoogle Scholar
  12. 12.
    Kim K, Park I-C (2006) Combined image signal processing for CMOS image sensors. In: IEEE international symposium on circuits and system (ISCAS)Google Scholar
  13. 13.
    van Dalen E, Pestana S, van Wel A (2006) An integrated, low-power processor for image signal processing. In: IEEE international symposium on multimedia (ISM)Google Scholar
  14. 14.
    Bong K et al (2014) An 1.61 mW Mixed-signal column processor for BRISK feature extraction in CMOS image sensor. IEEE international symposium on circuits and systems (ISCAS)Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2016

Authors and Affiliations

  1. 1.University of Wisconsin-MadisonMadisonUSA

Personalised recommendations