Digital neuromorphic (nm) sensor array, detector, engine and methodologies
AssigneesVolkswagen Aktiengesellschaft, Audi AG, Porsche AG
InventorsEdmund Dawes ZINK, Douglas Allen HAUGER, Lutz JUNGE, Luis Marcial HERNANDEZ GONZALEZ, Jerramy L. GIPSON, Anh VU, Martin HEMPEL, Nikhil J. GEORGE
Life of this patent
Estimating the term…
Abstract
A system and methodologies for neuromorphic vision simulate conventional analog NM system functionality and generate digital NM image data that facilitate improved object detection, classification, and tracking.
Claims44
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
(canceled)
A neuromorphic vision system generating and processing image data, the system comprising:
- a composite image sensor comprised of a plurality of photoreceptors for generating image data indicating whether an intensity value measured by each photoreceptor exceeds a threshold;
- a plurality of computational elements corresponding to the plurality of photoreceptors, wherein each of the plurality of computational elements generates image spike data for the respective corresponding photoreceptor based on the image data generated by at least two of the plurality of photoreceptors including the respective corresponding photoreceptor and a photoreceptor neighboring the respective corresponding photoreceptor;
- and
- a digital neuromorphic engine including one or more processors running software configured to generate, based on the generated image spike data, digital neuromorphic output data that includes velocity vector data representing a velocity space that is a spatial and temporal representation of the image data.
A method for generating and processing neuromorphic vision image data, the method comprising:
- generating image data using a plurality of photoreceptors;
- generating spike data using a plurality of computation elements, the spike data indicating whether the measured intensity values exceed a threshold, wherein each of the plurality of computational elements generates spike data for the respective corresponding photoreceptor based on the image data generated by at least two of the plurality of photoreceptors including the respective corresponding photoreceptor and a photoreceptor neighboring the respective corresponding photoreceptor;
- and
- generating digital neuromorphic output data using a digital neuromorphic engine coupled to the plurality of computational elements, wherein the digital neuromorphic output data includes velocity vector data generated based on the generated spike data and representing a velocity space that is a spatial and temporal representation of the image data generated by the plurality of photodetectors.
A non-transitory computer readable medium including software instructions for performing a method for generating and processing neuromorphic vision image data when the software is run on one or more processors, the method comprising:
- generating image data using a plurality of photoreceptors;
- generating spike data using a plurality of computation elements, the spike data indicating whether the measured intensity values exceed a threshold, wherein each of the plurality of computational elements generates spike data for the respective corresponding photoreceptor based on the image data generated by at least two of the plurality of photoreceptors including the respective corresponding photoreceptor and a photoreceptor neighboring the respective corresponding photoreceptor;
- and
- generating digital neuromorphic output data using a digital neuromorphic engine coupled to the plurality of computational elements, wherein the digital neuromorphic output data includes velocity vector data generated based on the generated spike data and representing a velocity space that is a spatial and temporal representation of the image data generated by the plurality of photodetectors.
A digital neuromorphic engine comprising:
- one or more processors running software configured to generate digital neuromorphic output data that includes velocity vector data representing a velocity space that is a spatial and temporal representation of image data,
- wherein the image data is generated by a composite image sensor comprised of a plurality of photoreceptors,
- wherein the image data indicates whether an intensity value measured by each photoreceptor exceeds a threshold,
- wherein a plurality of computational elements corresponding to the plurality of photoreceptors generate image spike data for the respective corresponding photoreceptor based on the image data generated by at least two of the plurality of photoreceptors including the respective corresponding photoreceptor and a photoreceptor neighboring the respective corresponding photoreceptor, and
- wherein the one or more processors generate the digital neuromorphic output data based on the generated image spike data.
Dependencies are inferred from the claim text.