Bedding System with a CNN Based Machine Vision Process

Abstract

A bedding system uses a convolutional neural network (CNN)-based machine vision to makes adjustments for comfort and/or support. The machine vision process identifies a body position by using a trained CNN that receives a pressure image and identifies a body position. The body position may be determined by classifying the pressure image into a predetermined body position classification. The machine vision process includes at least one trained CNN that determines joint locations. The machine vision tracks pressure accumulated at joints over time.

What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 receiving a set of pressure data measured by pressure sensors of a body support system, the set of pressure data comprising pressure values corresponding to different locations of the body support system, the pressure values taken when the body support system supporting an individual;   applying one or more machine learning models to analyze the set of pressure data to identify locations of a joint of the individual;   analyzing the set of pressure data to track pressure exerted on the joint over time; and   transmitting an alert in response to the pressure exerted on the joint exceeding a threshold level.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the set of pressure data corresponds to a two-dimensional pressure image. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the one or more machine learning models comprise a first machine learning model that determines a position of the individual and a second machine learning model that determines the locations of the joint of the individual. 
     
     
         4 . The computer-implemented method of  claim 3 , wherein the first machine learning model is a convolutional neural network. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein the alert comprising a message that the individual should change a position. 
     
     
         6 . The computer-implemented method of  claim 1 , further comprising:
 adjusting a comfort and/or support of the body support system based on the pressure exerted on the joint.   
     
     
         7 . The computer-implemented method of  claim 1 , further comprising:
 transmitting data for displaying a two-dimensional pressure image of the individual.   
     
     
         8 . The computer-implemented method of  claim 7 , wherein the two-dimensional pressure image displays different levels of pressure measurements with in different shadings and/or colors. 
     
     
         9 . The computer-implemented method of  claim 1 , further comprising:
 determining a position classification for a body position of the individual, the position classification selected from a list that comprises a leftside-sleeping classification, a rightside-sleeping classification, a prone-sleeping classification, and a supine-sleeping classification.   
     
     
         10 . The computer-implemented method of  claim 1 , wherein the body support system is a bedding system. 
     
     
         11 . A system comprising:
 a body support system comprising pressure sensors that are configured to generate a set of pressure data comprising pressure values correspond to different locations of the body support system, the pressure values taken when the body support system supporting an individual;   a computer in communication with the body support system, the computer configured to:
 receive the set of pressure data measured by the body support system; 
 apply one or more machine learning models to analyze the set of pressure data to identify locations of a joint of the individual; 
 analyze the set of pressure data to track pressure exerted on the joint over time; and 
 transmit an alert in response to the pressure exerted on the joint exceeding a threshold level. 
   
     
     
         12 . The system of  claim 11 , wherein the set of pressure data corresponds to a two-dimensional pressure image. 
     
     
         13 . The system of  claim 11 , wherein the one or more machine learning models comprise a first machine learning model that determines a position of the individual and a second machine learning model that determines the locations of the joint of the individual. 
     
     
         14 . The system of  claim 13 , wherein the first machine learning model is a convolutional neural network. 
     
     
         15 . The system of  claim 11 , wherein the alert comprising a message that the individual should change a position. 
     
     
         15 . The system of  claim 11 , wherein the computer is further configured to:
 adjust a comfort and/or support of the body support system based on the pressure exerted on the joint.   
     
     
         17 . The system of  claim 11 , wherein the computer is further configured to:
 transmit data for displaying a two-dimensional pressure image of the individual.   
     
     
         18 . The system of  claim 17 , wherein the two-dimensional pressure image displays different levels of pressure measurements with in different shadings and/or colors. 
     
     
         19 . The system of  claim 11 , wherein the computer is further configured to:
 determine a position classification for a body position of the individual, the position classification selected from a list that comprises a leftside-sleeping classification, a rightside-sleeping classification, a prone-sleeping classification, and a supine-sleeping classification.   
     
     
         20 . The system of  claim 11 , wherein the body support system is a bedding system.