DocumentCode :
981738
Title :
Analog VLSI focal-plane array with dynamic connections for the estimation of piecewise-smooth optical flow
Author :
Stocker, Alan A.
Author_Institution :
Center for Neural Sci., New York Univ., NY, USA
Volume :
51
Issue :
5
fYear :
2004
fDate :
5/1/2004 12:00:00 AM
Firstpage :
963
Lastpage :
973
Abstract :
An analog very large-scale integrated (aVLSI) sensor is presented that is capable of estimating optical flow while detecting and preserving motion discontinuities. The sensor´s architecture is composed of two recurrently connected networks. The units in the first network (the optical-flow network) collectively estimate two-dimensional optical flow, where the strength of their nearest-neighbor coupling determines the degree of motion integration. While the coupling strengths in our previous implementations were globally set and adjusted by the operator, they are now dynamically and locally controlled by a second on-chip network (the motion-discontinuity network). The coupling strengths are set such that visual motion integration is inhibited across image locations that are likely to represent motion boundaries. Results of a prototype sensor illustrate the potential of the approach and its functionality under real-world conditions.
Keywords :
VLSI; cellular neural nets; computer vision; image sequences; motion estimation; aVLSI sensor; analog VLSI focal-plane array; cellular neural networks; coupling; dynamic connections; image locations; motion boundaries; motion discontinuities; motion segmentation; motion-discontinuity network; neuromorphic; optical-flow network; piecewise-smooth optical flow estimation; recurrent feedback; sensor architecture; visual motion integration; Image motion analysis; Integrated optics; Motion detection; Motion estimation; Optical arrays; Optical detectors; Optical fiber networks; Optical network units; Optical sensors; Very large scale integration; Cellular neural networks; dynamic connectivity; gradient descent; line process; motion discontinuities; motion segmentation; neuromorphic; optimization; recurrent feedback;
fLanguage :
English
Journal_Title :
Circuits and Systems I: Regular Papers, IEEE Transactions on
Publisher :
ieee
ISSN :
1549-8328
Type :
jour
DOI :
10.1109/TCSI.2004.827619
Filename :
1296808
Link To Document :
بازگشت