Issue No. 03 - May/June (1992 vol. 12)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/40.141602
<p>The heterogeneous vision architecture that satisfies the computing demands of real-time computer vision by providing parallelism in three different forms is described. A pipeline of digital signal processing (DSP) chips initially processes signals. Then a SIMD associative processor array processes images and extract features, and a MIMD network of transputers processes extracted objects in parallel. The array's VLSI implementation, the processing modes available due to the use of content-addressable memory, and the means of achieving efficient 2-D interprocessor communication in the linear array are described. An application as a vehicle number plate recognition system is presented.</p>
A. W. Duller et al., "An Associative Processing Module for a Heterogeneous Vision Architecture," in IEEE Micro, vol. 12, no. , pp. 42-55, 1992.