The Community for Technology Leaders
Computer Architectures for Machine Perception, International Workshop on (2000)
Padova, Italy
Sept. 11, 2000 to Sept. 13, 2000
ISBN: 0-7695-0740-9
pp: 117
S.P. Sabatini , Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
P. Cavalleri , Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
F. Solari , Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
G.M. Bisio , Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
ABSTRACT
A computational architecture for direct estimation of heading direction from optic flow is proposed. By representing optic flow information as undulatory spatiotemporal patterns, global first-order differential analysis of the optic flow is reconducted to spatiotemporal filtering operations with local kernels characterized with respect to the fixation point(gaze). These operations can be mapped with high efficiency on analog architectures based on structured arrays of cells reacting collectively to spatiotemporal input stimuli. By observing the overall distribution of cells' activity, it is possible to gain information on the orientation of the heading in the retinal reference frame and on the angle between the heading and the gaze directions.
INDEX TERMS
image sequences; egomotion parameters; optic flow; heading direction; undulatory spatiotemporal patterns; differential analysis; retinal reference frame
CITATION

S. Sabatini, P. Cavalleri, G. Bisio and F. Solari, "Recovering 3-D Egomotion Parameters from Optic Flow: From Structural Principles to Analog Architectures," Computer Architectures for Machine Perception, International Workshop on(CAMP), Padova, Italy, 2000, pp. 117.
doi:10.1109/CAMP.2000.875966
94 ms
(Ver 3.3 (11022016))