SCoPE: Towards a Systolic Array for SVM Object Detection

This paper presents SCoPE (systolic chain of processing elements), a first step towards the realization of a generic systolic array for support vector machine (SVM) object classification in embedded image and video applications. SCoPE provides efficient memory management, reduced complexity, and efficient data transfer mechanisms. The proposed architecture is generic and scalable, as the size of the chain, and the kernel module can be changed in a plug and play approach without affecting the overall system architecture. These advantages provide versatility, scalability and reduced complexity that make it ideal for embedded applications. Furthermore, the SCoPE architecture is intended to be used as a building block towards larger systolic systems for multi-input or multi-class classification. Simulation results indicate real-time performance, achieving face detection at ~33 frames per second on an FPGA prototype.

[1]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Srihari Cadambi,et al.  A Massively Parallel Digital Learning Processor , 2008, NIPS.

[4]  A. Boni,et al.  A reconfigurable parallel architecture for SVM classification , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[5]  Davide Anguita,et al.  A digital architecture for support vector machines: theory, algorithm, and FPGA implementation , 2003, IEEE Trans. Neural Networks.

[6]  D. Houzet,et al.  Implementation of the SVM neural network generalization function for image processing , 2000, Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception.

[7]  Anupam Basu,et al.  Embedded Support Vector Machine : Architectural Enhancements and Evaluation , 2007, 20th International Conference on VLSI Design held jointly with 6th International Conference on Embedded Systems (VLSID'07).

[8]  Rasmus Ulslev Pedersen,et al.  An Embedded Support Vector Machine , 2006, 2006 International Workshop on Intelligent Solutions in Embedded Systems.

[9]  Gert Cauwenberghs,et al.  Kerneltron: support vector "machine" in silicon , 2003, IEEE Trans. Neural Networks.

[10]  Daniela Dragomirescu,et al.  Object Recognition System-on-Chip Using the Support Vector Machines , 2005, EURASIP J. Adv. Signal Process..