A Reconfigurable FPGA System for Parallel Independent Component Analysis

A run-time reconfigurable field programmable gate array (FPGA) system is presented for the implementation of the parallel independent component analysis (ICA) algorithm. In this work, we investigate design challenges caused by the capacity constraints of single FPGA. Using the reconfigurability of FPGA, we show how to manipulate the FPGA-based system and execute processes for the parallel ICA (pICA) algorithm. During the implementation procedure, pICA is first partitioned into three temporally independent function blocks, each of which is synthesized by using several ICA-related reconfigurable components (RCs) that are developed for reuse and retargeting purposes. All blocks are then integrated into a design and development environment for performing tasks such as FPGA optimization, placement, and routing. With partitioning and reconfiguration, the proposed reconfigurable FPGA system overcomes the capacity constraints for the pICA implementation on embedded systems. We demonstrate the effectiveness of this implementation on real images with large throughput for dimensionality reduction in hyperspectral image (HSI) analysis.

[1]  Jagath C. Rajapakse,et al.  Comparative study of implementing ICNNs on FPGAs , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[2]  Wesley E. Snyder,et al.  Band selection using independent component analysis for hyperspectral image processing , 2003, 32nd Applied Imagery Pattern Recognition Workshop, 2003. Proceedings..

[3]  M. Lennon,et al.  Independent component analysis as a tool for the dimensionality reduction and the representation of hyperspectral images , 2001, IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217).

[4]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[5]  Gert Cauwenberghs,et al.  Mixed-signal real-time adaptive blind source separation , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[6]  Hairong Qi,et al.  Parallel ICA and its hardware implementation in hyperspectral image analysis , 2004, SPIE Defense + Commercial Sensing.

[7]  Soo-Young Lee,et al.  Implementation of infomax ICA algorithm with analog CMOS circuits , 2001 .

[8]  Monk-Ping Leong,et al.  Pilchard - A Reconfigurable Computing Platform with Memory Slot Interface , 2001, IEEE Symposium on Field-Programmable Custom Computing Machines.

[9]  Farook Sattar,et al.  Low-cost design and implementation of an ICA-based blind source separation algorithm , 2002, 15th Annual IEEE International ASIC/SOC Conference.

[10]  Kazuyoshi Itoh,et al.  An algebraic solution to independent component analysis , 2000 .

[11]  Marian Stewart Bartlett,et al.  Viewpoint Invariant Face Recognition using Independent Component Analysis and Attractor Networks , 1996, NIPS.

[12]  Anis Nurashikin Nordin,et al.  Design of FPGA ICA for hyperspectral imaging processing , 2001, SPIE Defense + Commercial Sensing.

[13]  David A. Landgrebe,et al.  Some fundamentals and methods for hyperspectral image data analysis , 1999, Photonics West - Biomedical Optics.

[14]  Yu Wei,et al.  FPGA implementation of non-iterative ICA for detecting motion in image sequences , 2002, 7th International Conference on Control, Automation, Robotics and Vision, 2002. ICARCV 2002..

[15]  Terrence J. Sejnowski,et al.  ICA Mixture Models for Unsupervised Classification of Non-Gaussian Classes and Automatic Context Switching in Blind Signal Separation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .

[17]  I. Ginsberg,et al.  Unsupervised hyperspectral image analysis using independent component analysis , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[18]  Andreas G. Andreou,et al.  Analog CMOS integration and experimentation with an autoadaptive independent component analyzer , 1995 .

[19]  P.H.W. Leong,et al.  Pilchard — a reconfigurable computing platform with memory slot interface , 2001, The 9th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM'01).