A programmable focal-plane MIMD image processor chip

被引:44
作者
Etienne-Cummings, R [1 ]
Kalayjian, ZK
Cai, DH
机构
[1] Johns Hopkins Univ, Dept Elect & Comp Engn, Baltimore, MD 21218 USA
[2] USA, Res Labs, Adelphi, MD 20783 USA
[3] Intel Corp, Folsom, CA 95630 USA
基金
美国国家科学基金会;
关键词
edge detection chip; focal-plane processing; image processor chip; orientation detection chip; programmable analog computation; vision chip;
D O I
10.1109/4.896230
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
An 80 x 78 pixels vision chip for focal-plane image processing is presented. The chip employs a Multiple-Instruction-Multiple-Data (MIMD) architecture to provide five spatially processed images in parallel. The size, configuration, and coefficients of the spatial kernels are programmable. The chip's architecture allows the photoreceptor cells to be small and packed densely by performing all computations on the read-out, away from the array. The processing core uses digitally programmed current-mode analog computation. Operating at 9.6K frames/s in 800-lux ambient light, the chip consumes 4 mW from a 2.5-V power supply. Performing II x II spatial convolutions, an equivalent computation (5.5 bit scale-accumulate) rate of 12.4 GOPS/mW is achieved using 22 mm(2) in a 1.2-mum CMOS process, The application of the chip to line-segment orientation detection is also presented.
引用
收藏
页码:64 / 73
页数:10
相关论文
共 27 条
[1]  
[Anonymous], VISUAL PERCEPTION
[2]  
BAKER R, 1998, CMOS CIRCUIT DESING
[3]  
Boahen K., 1999, P MICR GRAN SPAIN MA
[4]  
BOAHEN KA, 1992, ADV NEUR IN, V4, P764
[5]   A SILICON VLSI OPTICAL SENSOR FOR PATTERN-RECOGNITION [J].
CAMP, WO ;
VANDERSPIEGEL, J .
SENSORS AND ACTUATORS A-PHYSICAL, 1994, 43 (1-3) :188-195
[7]  
CHANG HM, 1998, P 1998 IEEE INT S 2, P429
[8]   The design of rotation-invariant pattern recognition using the silicon retina [J].
Chiu, CF ;
Wu, CY .
IEEE JOURNAL OF SOLID-STATE CIRCUITS, 1997, 32 (04) :526-534
[9]  
CHO K, 1998, P IEEE INT JOINT C 1, P569
[10]   Mixed-signal VLSI architecture for real-time computer vision [J].
Dallaire, S ;
Tremblay, M ;
Poussart, D .
REAL-TIME IMAGING, 1997, 3 (05) :307-317