SCENE UNDERSTANDING USING A NEUROSYNAPTIC SYSTEM

Patent №

US 10,846,567

Granted

2020-11-24

Filed 2019

Owner

INTERNATIONAL BUSINESS MACHINES CORPORATION

AI components

3

ml · vision · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16592662

Embodiments of the invention provide a method for scene understanding based on a sequence of image frames. The method comprises converting each pixel of each image frame to neural spikes, and extracting features from the sequence of image frames by processing neural spikes corresponding to pixels of the sequence of image frames. The method further comprises encoding the extracted features as neural spikes, and classifying the extracted features.

Machine learningVisionAI hardwareG06V 10/451G06F 18/214G06F 18/24G06N 3/0499G06N 3/065G06N 3/08G06N 3/09G06T 7/246+7 more

AI classification

Vision1.00
Machine learning1.00
AI hardware1.00
Speech0.26
Knowledge representation0.07
Natural language0.07
Evolutionary computation0.00
Planning0.00

Ownership

INTERNATIONAL BUSINESS MACHINES CORPORATION

assignment · 506300510

Assignors

ANDREOPOULOS, ALEXANDER, APPUSWAMY, RATHINAKUMAR, DATTA, PALLAB, ESSER, STEVEN K., MODHA, DHARMENDRA S.

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC