A real-time vision system using an integrated memory array processor prototype

Machine Vision and Applications - Tập 7 - Trang 220-228 - 1994
Yoshihiro Fujita1, Nobuyuki Yamashita1, Shin'ichiro Okazaki1
1Information Technology Research Laboratory, NEC Corporation, Kanagawa, Japan

Tóm tắt

This paper describes a real-time vision system (RVS) architecture and performance and its use of an integrated memory array processor (IMAP) prototype. This prototype integrates eight 8-bit processors and a 144-kbit SRAM on a single chip. The RVS was developed with 64 IMAP prototypes connected in series in a 512 processor-system configuration. A host workstation can access the memory on the IMAP prototypes directly through a random access port. Images are inputted and outputted at high speed through serial access ports. The RVS performance is shown in real-time road-image processing and in a neural network simulation, as well as in low-level image processing algorithms, such as filtering, histograms, discrete cosine transform (DCT), and rotation. The RVS image processing is shown to be much faster than the video rate.

Tài liệu tham khảo

Batcher KE (1980) Design of a massively parallel processor. IEEE Trans Comput 29:836–840 Fountain TJ, Matthew KN, Duff MJB (1988) The CLIP7A image processor. IEEE Trans Patt Anal Machine Intell 10:310–319 Fujita Y, Yamashita N, Okazaki S (1992) IMAP: integrated memory array processor. J Circuits Syst Comput 2:227–245 Hammerstrom D (1990) A VLSI architecture for high-performance, low-cost, on-chip learning. International Joint Conference on Neural Networks 2:537–544 Hills WD (1985) The connection machine. MIT Press, Cambridge, Mass Ishimoto S (1985) A 256 k dual port memory. International Solid-State Circuits Conference 38-39 Kato H, Yoshizawa H, Iciki H, Asakawa K (1990) A parallel neurocomputer architecture towards billion connection updates per second. International Joint Conference on Neural Networks 2:47–50 Lea RM, Krikelis A (1990) ASP modules: cost effective building blocks for real-time computer vision. Parallel Architecture for Image Processing, SPIE 1246:45–56 Nickols JR (1992) The design of the MasPar MP-2: a cost effective massively parallel vomputer. MasPar Computer Corporation Pinkham R, Novak M, Guttag K (1983) Video RAM excels at fast graphics. Electronic Design, vol. 31, No. 17: 161–171 Schmitt LA (1988) The AIS-5000 parallel processor. IEEE Trans Patt Anal Machine Intell 10:320–330 Tanaka A (1986) A rotation method for raster image using skew transformation. Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp 272–277 Yasunaga M, Masuda N, Asai M, Yamada M, Masaki A, Hirai Y (1989) A wafer scale integration neural network utilizing completely digital circuits. International Joint Conference on Neural Networks 2:213–217