Accelerating FPGA-based evolution of wavelet transform filters by optimized task scheduling

Adaptive embedded systems are required in various applications. This work addresses these needs in the area of adaptive image compression in FPGA devices. A simplified version of an evolution strategy is utilized to optimize wavelet filters of a Discrete Wavelet Transform algorithm. We propose an adaptive image compression system in FPGA where optimized memory architecture, parallel processing and optimized task scheduling allow reducing the time of evolution. The proposed solution has been extensively evaluated in terms of the quality of compression as well as the processing time. The proposed architecture reduces the time of evolution by 44% compared to our previous reports while maintaining the quality of compression unchanged with respect to existing implementations. The system is able to find an optimized set of wavelet filters in less than 2min whenever the input type of data changes.

[1]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

[2]  Timothy G. W. Gordon,et al.  Exploiting development to enhance the scalability of hardware evolution , 2005 .

[3]  George Marsaglia.  Normal (Gaussian) random variables for supercomputers , 2004, The Journal of Supercomputing.

[4]  Lukás Sekanina.  Virtual Reconfigurable Circuits for Real-World Applications of Evolvable Hardware , 2003, ICES.

[5]  Moritoshi Yasunaga,et al.  An Online EHW Pattern Recognition System Applied to Sonar Spectrum Classification , 2007, ICES.

[6]  Lukás Sekanina,et al.  An Evolvable Combinational Unit for FPGAs , 2004, Comput. Artif. Intell..

[7]  Lukás Sekanina,et al.  Evolutionary design and optimization of Wavelet Transforms for image compression in embedded systems , 2010, 2010 NASA/ESA Conference on Adaptive Hardware and Systems.

[8]  Benjamin Belzer,et al.  Wavelet filter evaluation for image compression , 1995, IEEE Trans. Image Process..

[9]  Wim Sweldens,et al.  The lifting scheme: a construction of second generation wavelets , 1998 .

[10]  G. Masera,et al.  A VLSI architecture for IWT (integer wavelet transform) , 2000, Proceedings of the 43rd IEEE Midwest Symposium on Circuits and Systems (Cat.No.CH37144).

[11]  T. Jayachandra Prasad,et al.  Effective Image Compression using Evolved Wavelets , 2012 .

[12]  Fred L. Drake,et al.  The Python Language Reference Manual , 1999 .

[13]  Lukás Sekanina,et al.  Evolutionary Approach to Improve Wavelet Transforms for Image Compression in Embedded Systems , 2011, EURASIP J. Adv. Signal Process..

[14]  Andreas Tockhorn,et al.  Rapid Evolution of Time-Efficient Packet Classifiers , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[15]  Gianluca Piccinini,et al.  Novel JPEG 2000 Compliant DWT and IWT VLSI Implementations , 2003, J. VLSI Signal Process..

[16]  Lukas Sekanina,et al.  An evolvable hardware system in Xilinx Virtex II Pro FPGA , 2007 .

[17]  Jin Wang,et al.  Implementing Multi-VRC Cores to Evolve Combinational Logic Circuits in Parallel , 2007, ICES.

[18]  Travis E. Oliphant,et al.  Python for Scientific Computing , 2007, Computing in Science & Engineering.

[19]  Geert Uytterhoeven.  Wavelets: software and applications , 1999 .

[20]  Anil K. Jain,et al.  FVC2000: Fingerprint Verification Competition , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Frank W. Moore,et al.  A differential evolution algorithm for optimizing signal compression and reconstruction transforms , 2008, GECCO '08.

[22]  Wim Sweldens,et al.  An Overview of Wavelet Based Multiresolution Analyses , 1994, SIAM Rev..

[23]  A. E. Eiben,et al.  Introduction to Evolutionary Computing , 2003, Natural Computing Series.

[24]  Marco D. Santambrogio,et al.  A direct bitstream manipulation approach for Virtex4-based evolvable systems , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[25]  Lukás Sekanina,et al.  Hardware Accelerators for Cartesian Genetic Programming , 2008, EuroGP.

[26]  Lukás Sekanina,et al.  High Level Validation of an Optimization Algorithm for the Implementation of Adaptive Wavelet Transforms in FPGAs , 2010, 2010 13th Euromicro Conference on Digital System Design: Architectures, Methods and Tools.

[27]  Lukas Sekanina,et al.  Hardware Accelerator of Cartesian Genetic Programming with Multiple Fitness Units , 2012 .

[28]  Risto Miikkulainen,et al.  Evolving Wavelets Using a Coevolutionary Genetic Algorithm and Lifting , 2004, GECCO.

[29]  John R. Koza,et al.  Genetic Programming III: Darwinian Invention & Problem Solving , 1999 .

[30]  Enrico Magli,et al.  Optimization and implementation of the integer wavelet transform for image coding , 2002, IEEE Trans. Image Process..

[31]  W. Sweldens.  The Lifting Scheme: A Custom - Design Construction of Biorthogonal Wavelets "Industrial Mathematics , 1996 .

[32]  Teresa Riesgo,et al.  Bio-inspired FPGA architecture for self-calibration of an image compression core based on wavelet transforms in embedded systems , 2011, Microtechnologies.

[33]  P. Nordin.  Genetic Programming III - Darwinian Invention and Problem Solving , 1999 .

[34]  Frank W. Moore,et al.  Improved multiresolution analysis transforms for satellite image compression and reconstruction using evolution strategies , 2009, GECCO '09.

[35]  Andres Upegui,et al.  Evolving Hardware with Self-reconfigurable connectivity in Xilinx FPGAs , 2006, First NASA/ESA Conference on Adaptive Hardware and Systems (AHS'06).

[36]  Lorenz Huelsbergen,et al.  Evolving oscillators in silico , 1999, IEEE Trans. Evol. Comput..

[37]  Kyrre Glette,et al.  Design and Implementation of Scalable Online Evolvable Hardware Pattern Recognition Systems , 2008 .

[38]  A..  A VHDL Core for Intrinsic Evolution of Discrete Time Filters with Signal Feedback , 2005 .

[39]  Jin Wang,et al.  Design and implementation of a virtual reconfigurable architecture for different applications of intrinsic evolvable hardware , 2008, IET Comput. Digit. Tech..

[40]  Adrian Thompson,et al.  Silicon evolution , 1996 .

[41]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[42]  Frank W. Moore,et al.  The best fingerprint compression standard yet , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[43]  Chaitali Chakrabarti,et al.  A Survey on Lifting-based Discrete Wavelet Transform Architectures , 2006, J. VLSI Signal Process..

[44]  Gunnar Tufte,et al.  Evolving an adaptive digital filter , 2000, Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware.

[45]  Brendan Babb,et al.  Optimized satellite image compression and reconstruction via evolution strategies , 2009, Defense + Commercial Sensing.

[46]  TomasM art ´ inek.  An Evolvable Image Filter: Experimental Evaluation of a Complete Hardware Implementation in FPGA , 2005 .

[47]  Zdenÿek Vaÿ ´ õÿ.  HARDWARE ACCELERATOR OF CARTESIAN GENETIC PROGRAMMING WITH MULTIPLE FITNESS UNITS , 2010 .

[48]  Rubén Salvador Perea,et al.  Implementation of bio-inspired adaptive wavelet transforms in FPGAs. Modeling, validation and profiling of the algorithm , 2010 .

[49]  Yang Zhang,et al.  Intrinsic Evolvable Hardware in Digital Filter Design , 2004, EvoWorkshops.

[50]  Guido van Rossum,et al.  The Python language reference manual: for Python version 3.2 , 2011 .

[51]  Ronald F. DeMara,et al.  Layered Approach to Intrinsic Evolvable Hardware using Direct Bitstream Manipulation of Virtex II Pro Devices , 2007, 2007 International Conference on Field Programmable Logic and Applications.

[52]  Lukás Sekanina,et al.  On Evolutionary Synthesis of Linear Transforms in FPGA , 2008, ICES.

[53]  Gonzalo Seco-Granados,et al.  A Reduced Complexity Approach to IAA Beamforming for Efficient DOA Estimation of Coherent Sources , 2011, EURASIP J. Adv. Signal Process..

[54]  John D. Hunter,et al.  Matplotlib: A 2D Graphics Environment , 2007, Computing in Science & Engineering.