Title :
A micropower centroiding vision processor
Author :
Constandinou, Timothy G. ; Toumazou, Christofer
Author_Institution :
Inst. of Biomed. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK
fDate :
6/1/2006 12:00:00 AM
Abstract :
A biologically-inspired hybrid vision chip is presented for real-time object-based processing for tasks such as centroiding, sizing and counting of enclosed objects. This system presents the first silicon retina capable of centroiding and sizing multiple objects in true parallel fashion. Based on a novel distributed algorithm, this approach uses the input image to enclose a feedback loop to realize a data-driven pulsating action. The sensor provides a resolution of 48 × 48 pixels with a 85 μm×85 μm pixel footprint and has been measured to consume 243 μW at 1.8-V supply, achieving an equivalent computational efficiency of 724.64 MIPS/mW with a 500-μs process time.
Keywords :
CMOS image sensors; distributed algorithms; object detection; parallel processing; 1.8 V; 2304 pixels; 243 muW; 48 pixels; 500 mus; CMOS image sensor; biologically-inspired hybrid vision chip; centroiding; distributed algorithm; feedback loop; focal plane processing; object detection; parallel processing; real-time object-based processing; Cellular neural networks; Computational efficiency; Distributed algorithms; Filtering; Image processing; Object detection; Object segmentation; Retina; Silicon; Target tracking; CMOS image sensor; Centroiding; distributed algorithm; focal plane processing; micropower; object detection; parallel processing; silicon retina; target tracking; vision chip;
Journal_Title :
Solid-State Circuits, IEEE Journal of
DOI :
10.1109/JSSC.2006.874330