Parallel object recognition on an FPGA-based configurable computing platform

Object recognition involves identifying known objects in a given scene. It plays a key role in image understanding. Geometric hashing has been proposed as a technique for model-based object recognition in occluded scenes. However, parallel techniques are needed to realize real-time vision systems employing geometric hashing. In this paper, we develop a design technique for parallelizing geometric hashing on an FPGA-based platform. We first transform the hash table which contains symbolic data into a bit-level representation. By regularizing the data flow and exploiting bit-level parallelism in hardware, our design achieves high performance. Using our approach, given a scene consisting of 256 feature points, a probe can be performed in 1.65 milliseconds on an FPGA-based platform having 32 Xilinx 4062s. In earlier implementations, the same probe operation was performed in 240 milliseconds on a 32K-node CM2 and in 382 milliseconds on a 32-node CM5. Also, the same operation takes 40 milliseconds on a 32-node IBM SP-2. By parameterizing the application and the device characteristics, we derive an area-time efficient design based on these parameters. Furthermore, our approach can be applied to many geometric hashing methods and is portable to other FPGA devices.

[1]  Viktor K. Prasanna,et al.  Scalable Data Parallel Implementations of Object Recognition Using Geometric Hashing , 1994, J. Parallel Distributed Comput..

[2]  Viktor K. Prasanna,et al.  Fast parallel implementation of DFT using configurable devices , 1997, FPL.

[3]  Viktor K. Prasanna,et al.  A Fast Algorithm for Computing a Histogram on Reconfigurable Mesh , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Russ Miller,et al.  Meshes with reconfigurable buses , 1988 .

[5]  John Wawrzynek,et al.  Garp: a MIPS processor with a reconfigurable coprocessor , 1997, Proceedings. The 5th Annual IEEE Symposium on Field-Programmable Custom Computing Machines Cat. No.97TB100186).

[6]  Viktor K. Prasanna,et al.  A fast algorithm for computing histograms on a reconfigurable mesh , 1992, [Proceedings 1992] The Fourth Symposium on the Frontiers of Massively Parallel Computation.

[7]  André DeHon,et al.  Reconfigurable architectures for general-purpose computing , 1996 .

[8]  Yehezkel Lamdan,et al.  Geometric Hashing: A General And Efficient Model-based Recognition Scheme , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[9]  Peter M. Athanas,et al.  Wormhole run-time reconfiguration , 1997, FPGA '97.

[10]  Robert A. Hummel,et al.  Massively parallel model matching: geometric hashing on the Connection Machine , 1992, Computer.

[11]  Hungwen Li,et al.  Connection Autonomy in SIMD Computers: A VLSI Implementation , 1989, J. Parallel Distributed Comput..

[12]  Viktor K. Prasanna,et al.  An Optimal Sorting Algorithm on Reconfigurable Mesh , 1995, J. Parallel Distributed Comput..

[13]  Gerard Medioni,et al.  Object recognition using geometric hashing on the Connection Machine , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.