A low-power 490 mpixels/s hardware accelerator for pyramidal decomposition of images

This paper introduces a pyramidal decomposition system suitable for high frame rate and real-time applications. The presented system's architecture omits the image transpose block used in standard separable filters, and implements internal downsampling to reduce number of computations. The decomposition is implemented in form of a field programmable gate array (FPGA) hardware accelerator and the presented results show the low resource utilization of the design. The internal downsampling reduces the power consumption by an order of magnitude compared to state-of-the-art, which makes this accelerator an excellent addition to co-processors on mobile platforms.

[1]  Chin-Teng Lin,et al.  2-D digital filter architectures without global broadcast and some symmetry applications , 2009, 2009 IEEE International Symposium on Circuits and Systems.

[2]  Marios Pattichis,et al.  Real-time dynamically reconfigurable 2-D filterbanks , 2010, 2010 IEEE Southwest Symposium on Image Analysis & Interpretation (SSIAI).

[3]  Kun Gao,et al.  Implementation of real-time Laplacian pyramid image fusion processing based on FPGA , 2007, SPIE/COS Photonics Asia.

[4]  Sek M. Chai,et al.  Method of image fusion and enhancement using mask pyramid , 2011, 14th International Conference on Information Fusion.

[5]  M. Omair Ahmad,et al.  A Pipeline VLSI Architecture for Fast Computation of the 2-D Discrete Wavelet Transform , 2012, IEEE Transactions on Circuits and Systems I: Regular Papers.

[6]  Christos-Savvas Bouganis,et al.  A novel 2D filter design methodology for heterogeneous devices , 2005, 13th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM'05).

[7]  Gooitzen S. van der Wal.  Technical overview of the Sarnoff Acadia II vision processor , 2010 .

[8]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

[9]  Daniel Llamocca,et al.  Separable FIR Filtering in FPGA and GPU Implementations: Energy, Performance, and Accuracy Considerations , 2011, 2011 21st International Conference on Field Programmable Logic and Applications.

[10]  Yusuf Leblebici,et al.  Real-time hardware implementation of multi-resolution image blending , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[11]  Tian-Sheuan Chang,et al.  A 124 Mpixels/s VLSI Design for Histogram-Based Joint Bilateral Filtering , 2011, IEEE Transactions on Image Processing.

[12]  E. Reinhard.  Photographic Tone Reproduction for Digital Images , 2002 .

[13]  James Irvine,et al.  An FPGA Implementation of Pattern-Selective Pyramidal Image Fusion , 2006, 2006 International Conference on Field Programmable Logic and Applications.

[14]  Manoj Sachdev,et al.  Multiprocessor FPGA implementation of a 2D digital filter , 2011, 2011 24th Canadian Conference on Electrical and Computer Engineering(CCECE).

[15]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[16]  Narayanan Vijaykrishnan,et al.  SHARC: A streaming model for FPGA accelerators and its application to Saliency , 2011, 2011 Design, Automation & Test in Europe.

[17]  L.-D. Van.  A new 2-D systolic digital filter architecture without global broadcast , 2002, IEEE Trans. Very Large Scale Integr. Syst..