System apparatus and method for guiding user to comply with application-specific requirements
AssigneeGoodsize Inc.
InventorsDmitrii Ulianov, Sergei Sherman, Ilya Krotov
Life of this patent
Estimating the term…
Abstract
A system, device, and a method for guiding a user to comply with one or more application-specific requirements by using sequentially two or more neural networks run on one more video frame of a scene to detect at least one requirement of the one or more application-specific requirements. Upon the detection result, the application guides a user to adjust the scene based on the detection until the scene is adjusted to meet the application-specific requirements.
Claims16
A system for guiding a user to comply with one or more application-specific requirements comprising a user device comprises processing circuitry and one or more sensors, wherein the processing circuitry is configured to:
- receive one or more video frames which include an at least one image of a scene from the one or more sensors;
- run a first trained neural network of a plurality of trained neural networks on the at least one image to detect a first application-specific requirement of the one or more application-specific requirements based on a dataset, wherein the detection is done based on at least one or more images stored at the dataset;
- provide one or more directions to the user to adjust one or more elements in the scene until the first application-specific requirement is met;
- run a second trained neural network of the plurality of the trained neural networks to detect a second application-specific requirement that includes an angle between the legs and provide directions to the user to adjust the angle between the legs until a predefined angle between the legs is met;
- run a third trained neural network of the plurality of the trained neural networks to detect a third application-specific requirement that includes an angle between the arms and provide directions to the user to adjust the angle between the arms until a predefined angle between the arms is met;
- and
- run, one after another, all the other trained neural networks on all the other application-specific requirements and provide direction for each requirement until all the one or more application-specific requirements at the scene are met.
A product comprising one or more tangible computer-readable non-transitory storage media comprising program instructions for guiding a user to comply with one or more application-specific requirements, wherein execution of the program instructions of an application by one or more processors comprising:
- receiving one or more video frames which include an at least one image of a scene from the one or more sensors;
- running a first trained neural network of a plurality of trained neural networks on the at least one image to detect a first application-specific requirement of the one or more application-specific requirements based on a dataset, wherein the detection is done based on at least one or more images stored at the dataset;
- providing one or more directions to the user to adjust one or more elements in the scene until the first application-specific requirement is met;
- running a second trained neural network of the plurality of the trained neural networks to detect a second application-specific requirement that includes an angle between the legs and provide directions to the user to adjust the angle between the legs until a predefined angle between the legs is met;
- running a third neural network of the plurality of trained neural networks to detect a third application-specific requirement that includes an angle between the arms and provide directions to the user to adjust the angle between the arms until a predefined angle between the arms is met;
- and
- running, one after another, all other trained neural networks on all the other application-specific requirements and providing direction for each requirement until all the one or more application-specific requirements at the scene are met.
Dependencies are inferred from the claim text.