DERIVING INSIGHTS INTO MOTION OF AN OBJECT THROUGH COMPUTER VISION
Introduced here are computer programs that are able to generate computer vision data through local analysis of image data (also referred to as “raw data” or “input data”). The image data may be representative of one or more digital images that are generated by an image sensor. Also introduced here are apparatuses for generating and handling the image data and computer vision data.
1 . A computing device comprising:
an image sensor that is configured to generate image data that is representative of one or more digital images of an environment in which an individual is situated;
a processor that is configured to:
apply, to the image data, a neural network that predicts a pose of the individual in each digital image of the one or more digital images, so as to produce one or more predicted poses, and
encode the one or more predicted poses in a data structure; and
wireless communication circuitry that is configured to communicate, via a network, the data structure to another computing device with a graphics processing unit, at which the data structure is decoded for storage, visualization, or analysis of the one or more predicted poses.
2 . The computing device of claim 1 ,
wherein the processor is further configured to encode the image data in a second data structure; and
wherein the wireless communication circuitry is further configured to communicate, via the network, the second data structure to the other computing device, at which the second data structure is decoded and the image data is stored.
3 . The computing device of claim 1 , wherein each predicted pose of the one or more predicted poses indicates locations of a plurality of anatomical features in two-dimensional space.
4 . The computing device of claim 1 , wherein each predicted pose of the one or more predicted poses indicates locations of a plurality of anatomical features in three-dimensional space.
5 . The computing device of claim 1 , wherein the wireless communication circuitry is further configured to communicate, via the network, metadata that identifies the computing device as a source of the one or more predicted poses to the other computing device.
6 . The computing device of claim 5 , wherein the processor is further configured to append the metadata to the one or more predicted poses, or encode the metadata in the data structure, prior to transmission to the other computing device.
7 . The computing device of claim 1 , wherein the wireless communication circuitry is further configured to communicate, via the network, metadata that includes information related to, or derived from, the one or more predicted poses or the image data.
8 . A method performed a first computer program executing on a first computing device with a graphics processing unit and a second computer program executing on a second computing device with a central processing unit, the method comprising:
applying, by the second computer program, a computational model to a plurality of digital images that are generated by the second computing device to produce a plurality of outputs,
wherein each output of the plurality of outputs is representative of information regarding a spatial position of an individual as determined through analysis of a corresponding digital image of the plurality of digital images, and
wherein the plurality of outputs are collectively representative of computer vision data;
populating, by the second computer program, the computer vision data into a data structure that is transmitted to the first computing device; and
assessing, by the first computer program, health of the individual based on an analysis of the computer vision data.
9 . The method of claim 8 , further comprising:
posting, by the first computer program, a visualization that is representative of the individual and is created based on the computer vision data to an interface for review by a person.
10 . The method of claim 9 , wherein the person is a healthcare professional that is responsible for providing care and/or feedback to the individual, as the individual completes an exercise and is imaged by the second computing device.
11 . The method of claim 8 , wherein said assessing comprises determining musculoskeletal performance of the individual, and wherein the method further comprises:
receiving, by either the first computer program or the second computer program, input that is indicative of a request to initiate an exercise therapy session; and
causing, by either the first computer program or the second computer program, presentation of an instruction to the individual to perform an exercise;
wherein the plurality of digital images are generated by the second computing device as the individual performs the exercise.
12 . The method of claim 11 , wherein in response to a determination that the individual completed the exercise, either the first computer program or the second computer program presents another instruction to the individual to perform another exercise as part of the exercise therapy session.
13 . The method of claim 8 , wherein said assessing comprises performing fall detection based on the computer vision data.
14 . The method of claim 8 , wherein said assessing comprises performing gait analysis based on the computer vision data.
15 . The method of claim 8 , wherein said assessing comprises performing activity analysis based on the computer vision data, the activity analysis indicating an estimated level of effort being employed by the individual.
16 . The method of claim 8 , wherein said assessing comprises performing fine motor skill analysis based on the computer vision data.
17 . The method of claim 8 , wherein said assessing comprises performing range of motion analysis based on the computer vision data.
18 . The method of claim 8 , wherein said assessing comprises performing muscle fatigue analysis based on the computer vision data, the muscle fatigue analysis indicating an estimated level of fatigue being experienced by a muscle of the individual.
19 . The method of claim 8 , wherein said assessing comprises performing muscle distribution analysis based on the computer vision data, the muscle distribution analysis indicating an estimated location, size, and/or shape of a muscle of the individual.
20 . The method of claim 8 , wherein said assessing comprises performing body mass index (BMI) analysis based on the computer vision data.
21 . The method of claim 8 , wherein said assessing comprises performing blood flow analysis based on the computer vision data, the blood flow analysis indicating whether an estimated speed and/or volume of blood flow through the individual is abnormal.
22 . The method of claim 8 , wherein said assessing comprises performing temperature analysis based on the computer vision data, the temperature analysis indicating temperature along a surface of a body of the individual in at least two different locations.
23 . A method performed by a computer program that is executing on a computing device with a graphics processing unit, the method comprising:
acquiring, from a source external to the computing device, at least one data structure in which is encoded
(i) digital images of an individual performing an exercise, and
(ii) computer vision data that is representative of information regarding poses of the individual while performing the exercise, as determined through analysis of the digital images;
decoding the at least one data structure to obtain the digital images and the computer vision data; and
posting, to an interface, at least one of the digital images and a visualization that is representative of the individual and that is produced via an analysis of the computer vision data.