Back to results
US 2022/0092400 A1Published application
Method and system of highly efficient neural network image processing
AssigneeIntel Corporation
InventorsNoam Elron, Ben Berlin, Dmitry Rudoy, Amir Goren, Noam Levy
Life of this patent
Estimating the term…
Abstract
A method, system, and article of highly efficient neural network video image processing uses temporal correlations.
Claims25
A computer-implemented method of image processing, comprising:
- inputting image data of frames of a video sequence into a neural network with one or more upstream layers and one or more downstream layers relative to the upstream layers;
- and
- determining whether or not to turn off processing of at least one omission layer portion of at least one of the downstream layers, wherein the determining depends on a comparison between current features output from one or more of the upstream layers processing a current frame and a version of previous features of the neural network associated with a previous frame.
A system for image processing, comprising:
- memory storing image data of frames of a video sequence and neural network features;
- and
- processor circuitry forming at least one processor communicatively coupled to the memory, the at least one processor being arranged to operate by:
- inputting the image data into a neural network, wherein the neural network has one or more upstream layers and one or more downstream layers relative to the upstream layers, and
- determining whether or not to turn off processing of at least one omission layer portion of at least one of the downstream layers, wherein the determining depending on a correlation between current features output from one or more of the upstream layers processing a current frame and a version of previous features associated with a previous frame.
2 more elements
At least one non-transitory article having at least one computer readable medium comprising a plurality of instructions that in response to being executed on a computing device, cause the computing device to operate by:
- inputting image data of frames of a video sequence into a neural network with one or more upstream layers and one or more downstream layers relative to the upstream layers;
- and
- determining whether or not to turn off processing of at least one omission layer portion of at least one of the downstream layers wherein the determining depending on a correlation between current features output from one or more of the upstream layers processing a current frame and a version of previous features associated with a previous frame.
Dependencies are inferred from the claim text.