Various embodiments concern video patient monitoring with detection zones. Various embodiments can comprise a camera, a user interface, and a computing system. The computing system can be configured to perform various steps based on reception of a frame from the camera, including: calculate a background luminance of the frame; monitor for a luminance change of a zone as compared to one or more previous frames, the luminance change indicative of patient motion in the zone; and compare the background luminance to an aggregate background luminance, the aggregate background luminance based on the plurality of frames. If the background luminance changed by more than a predetermined amount, then the aggregate background luminance can be set to the background luminance, luminance information of the previous frames can be disregarded, and motion detection can be disregarded.

A system and method for human motion detection and tracking are disclosed. In one embodiment, an optical sensing instrument monitors a stage. A memory is accessible to a processor and communicatively coupled to the optical sensing instrument. The system captures a depth frame from the optical sensing instrument. The depth frame may include at each image element first coordinate values including a point related to a distance from the optical sensing instrument. The depth frame is converted into a designated depth frame format, which includes at each image element second coordinate values relative to the depth frame. Probability distribution models are applied to the designated depth frame format to identify a respective plurality of body parts. The position of each of the respective plurality of body parts in the designated depth frame is calculated as is the position of each of the plurality of body parts in the depth frame.

A system, method and article of manufacture are presented for assisting the fields of health care, kinesiology, and sports medicine. More specifically the method of the system measures the dynamics of the biomechanics of motion of a human patient or athlete and quantitatively determining the presence or absence of biomechanical abnormalities, classifying abnormalities that are present, developing or critiquing one or more diagnoses in terms of the biomechanics evidence supporting the classification, recommending an appropriate training or treatment regimen based on the diagnoses, and monitoring progress while the individual is under the training or treatment regimen.

Implementations illustrated herein discloses a method of controlling drug titration to a patient, the method including receiving, using a processor, a sequence of depth images, each depth image including depth information for at least a portion of the patient, determining, using the processor, a sequence of physiological signals for the patient based on the sequence of depth images, analyzing, using the processor, the sequence of physiological signals for the patient to determine a change in a condition of the patient, and generating a signal to a drug infusion pump in response to determining the change in the condition of the patient.

Method and system of training a machine learning neural network (MLNN) monitoring anatomical dynamics of a subject in motion. The method comprises receiving, in a first input layer of the MLNN, from a millimeter wave (mmWave) radar sensing device, mmWave radar point cloud data representing a first gait characteristic; receiving, in a second layer of the MLNN, from the mmWave radar sensing device, mmWave radar point cloud data representing a second gait characteristic; the first and the at least a second input layers being interconnected with an output layer via an intermediate layer having an initial matrix of weights; training a MLNN classifier based on a supervised classification establishing correlation between a degenerative condition of the subject at the output layer and the point cloud data; and adjusting the initial matrix of weights by backpropagation to increase correlation between the degenerative condition and the sets of point cloud data.

Methods and systems for temperature screening using a mobile device. In one example, a mobile temperature screening system may comprise a mobile device including a display, a memory, a processor, a thermal imaging camera, a visible light imaging camera, and a wireless communication capability. The processor may be configured to obtain a thermal image of a person and a visible light image of the person, determine a body temperature of the person based at least in part on the thermal image, and classify the person as having a normal body temperature when the body temperature of the person is below a threshold temperature. When the body temperature of the person exceeds the threshold temperature the processor may be configured to classify the person as having an elevated body temperature, generate a visual alert, and transmit the thermal image, the visible light image and the classification to a remote device.

A system and/or method that uses a body posture of a user to determine and modulate a content mode of a virtual reality system. The content mode may define the manner in which virtual reality content is presented to the user and/or the manner in which the user interacts with the virtual reality content. The user's body posture and/or a change in body posture may cause the content mode and/or the virtual reality content to change accordingly. In some implementations, primary content may be presented to the user according to a first content mode in response to the user sitting. Secondary virtual reality content may be presented to the user according to the second content mode in response to the user standing. As such, a user may initiate a change in the virtual reality content and/or the content mode by standing from a sitting posture and/or sitting from a standing posture.

A smart mirror can show live or recorded streaming video of an instructor performing a workout in a package that is attractive and unobtrusive enough to hang in a living room. The smart mirror includes a mirror surface with a fully reflecting section and a partially reflecting section. A display behind the partially reflecting section shows the video when the smart mirror is on and is almost invisible when the smart mirror is off. The smart mirror also has a speaker, a microphone, and a camera to enable a user to view the video content and interact with the instructor. The smart mirror may connect to the user's smart phone, a peripheral device (e.g., a Bluetooth speaker) to augment user experience, a biometric sensor to provide biometric data to assess user performance, and/or a network router to connect the smart mirror to a content provider, an instructor, and/or other users.

Augmented reality systems and methods for user health analysis. Methods for user health analysis may include collecting data for an initial prediction model and continuing to collect additional data based on one or more data criteria. The methods may further include updating the initial prediction model based on the additional data to produce a revised prediction model or causing an intervention to occur based on the additional data. The data may be collected by a display system including one or more sensors configured to collect user-specific data and a display device configured to present virtual content to a user. The display device may be configured to output light with variable wavefront divergence.

A recognition method executed by a processor, includes: acquiring positional relation between a plurality of sensors each of which senses a distance to an object; provisionally classifying an orientation of the object relative to each individual sensor included in the sensors into one of a plurality of classifications based on sensing data acquired by the individual sensor; calculating likelihood of each combination corresponding to the positional relation between the sensors based on a result of provisional classification of the orientation of the object relative to the individual sensor; and classifying the orientation of the object corresponding to each individual sensor in accordance with the calculated likelihood of each combination.