JSTS:Journal of Semiconductor Technology and Science

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지
DOI QR코드

DOI QR Code

A novel hardware design for SIFT generation with reduced memory requirement

  • Kim, Eung Sup (Both authors are with Inter-university Semiconductor Research Center, Department of Electrical Engineering, Seoul National University) ;
  • Lee, Hyuk-Jae (Both authors are with Inter-university Semiconductor Research Center, Department of Electrical Engineering, Seoul National University)
  • Received : 2012.08.23
  • Accepted : 2012.11.29
  • Published : 2013.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Scale Invariant Feature Transform (SIFT) generates image features widely used to match objects in different images. Previous work on hardware-based SIFT implementation requires excessive internal memory and hardware logic [1]. In this paper, a new hardware organization is proposed to implement SIFT with less memory and hardware cost than the previous work. To this end, a parallel Gaussian filter bank is adopted to eliminate the buffers that store intermediate results because parallel operations allow all intermediate results available at the same time. Furthermore, the processing order is changed from the raster-scan order to the block-by-block order so that the line buffer size storing the source image is also reduced. These techniques trade the reduction of memory size with a slight increase of the execution time and external memory bandwidth. As a result, the memory size is reduced by 94.4%. The proposed hardware for SIFT implementation includes the Descriptor generation block, which is omitted in the previous work [1]. The addition of the hardwired descriptor generation improves the computation speed by about 30 times when compared with the previous work.

Keywords

References

  1. V. Bonato, E. Marques, and G.A. Constantinides, "A Parallel Hardware Architecture for Scale and Rotation Invariant Feature Detection," IEEE Trans. on Circuits and Syst. Video Technology, vol. 18, no. 12, pp. 1703-1712, Dec. 2008. https://doi.org/10.1109/TCSVT.2008.2004936
  2. D. Lowe, "Distinctive image features from scaleinvariant keypoints," Int. Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, Jan. 2004. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  3. M. Grabner, H. Grabner, and H. Bischof, "Fast approximated SIFT," ACCV 2006, LNCS 3851, pp. 918-927, 2006.
  4. Y. Ke and R. Sukthankar, "PCA-SIFT: A more distinctive representation for local image descriptors," in Proc. IEEE CVPR, pp. 506-513, Washington, USA, 2004.
  5. K.G. Derpanis, E.T.H. Leung, and M. Sizintsev, "Fast Scale-Space Feature Representations by Generalized Integral Images," in Proc. IEEE ICIP, San Antonio, USA, 2007, pp. 521-524
  6. T. Lindeberg, "Scale-space for discrete signals," IEEE Trans. On Pattern Analysis and Machine Intelligence, vol. 12, no. 3, pp. 234-254, Apr. 1990. https://doi.org/10.1109/34.49051
  7. R. Hess. SIFT Feature Detector (Source Code). Available: http://blogs.oregonstate.edu/hess/code/sift/
  8. J.R. Magnus and H. Neudecker, Matrix Differential Calculus with Applications in Statistics and Econometrics, 2nd edition, Wiley, 1999.
  9. D.B. Williams and V. Madisetti, Digital Signal Processing Handbook, 1st edition, CRC Press, 1997.

Cited by

  1. SIFT Hardware Implementation for Real-Time Image Feature Extraction vol.24, pp.7, 2014, https://doi.org/10.1109/TCSVT.2014.2302535
  2. Hardware-Efficient Local Extrema Detection for Scale-Space Extrema Detection in SIFT Algorithm vol.E99.A, pp.12, 2016, https://doi.org/10.1587/transfun.E99.A.2507
  3. Complexity Reduction by Modified Scale-Space Construction in SIFT Generation Optimized for a Mobile GPU vol.27, pp.10, 2017, https://doi.org/10.1109/TCSVT.2016.2580400
  4. Design of a Convolutional Two-Dimensional Filter in FPGA for Image Processing Applications vol.6, pp.2, 2017, https://doi.org/10.3390/computers6020019
  5. Multiplier-Less Stream Processor for 2D Filtering in Visual Search Applications vol.28, pp.1, 2018, https://doi.org/10.1109/TCSVT.2016.2603068
  6. A novel SIFT architecture and ASIC implementation for real time SOC application pp.1573-1979, 2019, https://doi.org/10.1007/s10470-019-01419-9