Remote biometric monitoring systems may include a digital camera having a digital sensor, a processor, and a memory, all enclosed in a common housing. The processor of the camera may locally execute one or more algorithms to perform computer vision analysis of captured images of a sleeping subject, thereby determining an activity state of the subject. The activity state may include a sleep state. One or more environmental control devices may be adjusted automatically by the system based at least in part on the activity state.
Claim CLM-00001. 1. A system for remotely monitoring a sleeping subject, the system comprising:
a digital camera configured to capture images of a subject, the digital camera including a digital image sensor, one or more local processors in communication with the digital image sensor, and a memory, wherein the digital image sensor, the one or more local processors, and the memory are enclosed in a same housing, and wherein no part of the system is attached to the subject; a set of instructions stored in the memory of the digital camera and executable locally by the one or more local processors to:
receive a plurality of time-sequenced images of the subject from the digital image sensor;determine a position of a torso region of the subject, using an artificial intelligence module trained to determine a presence and a position of the subject in a subset of images of the time-sequenced plurality of images;define a bounding box that identifies where the subject is located in the image;determine a respiration pattern of the subject by performing a biometric analysis on the time-sequenced plurality of images using the position of the torso region within the bounding box determined by the artificial intelligence module, wherein:
determining the respiration pattern includes generating a time-varying number corresponding to respiration of the subject, wherein the time-varying number coincides with a depth and a length of each breath of the subject;cause an indicator corresponding to the time-varying number on a remote notification device to be presented; andanalyze motion outside of the bounding box defined by the artificial intelligence module; andflag a video clip for review based on greater than a threshold amount of motion being determined by analyzing the motion outside of the bounding box defined by the artificial intelligence module.
Claim CLM-00011. 11. A system for remotely monitoring a sleeping person, the system comprising:
a digital camera configured to capture images of a person, the digital camera including a digital image sensor, one or more local processors in communication with the digital image sensor, and a memory, wherein the digital image sensor, the one or more local processors, and the memory are enclosed in a same housing, and wherein no portion of the system is attached to the person; a remote notification device in communication with a user located out of sight of the person; and a set of instructions stored in the memory of the digital camera and executable locally by the one or more local processors to:
receive a plurality of time-sequenced images of the person from the digital image sensor;determine a position of a torso region of the person, using an artificial intelligence module trained to determine a presence and a position of the person, in at least one image of the time-sequenced plurality of images;define a bounding box that identifies where the subject is located in the image;determine a respiration pattern of the person by performing a biometric analysis on the plurality of time-sequenced images, wherein determining the respiration pattern includes generating a time-varying number corresponding to respiration of the person, such that the time-varying number coincides with a depth and a length of each breath of the person;cause an indicator corresponding to the time-varying number on the remote notification device to be displayed;analyze motion outside of the bounding box defined by the artificial intelligence module; andflag a video clip for review based on greater than a threshold amount of motion being determined by analyzing the motion outside of the bounding box defined by the artificial intelligence module.