Abstract: A mobile hyperspectral camera system is described. The mobile hyperspectral camera system comprises a mobile host device comprising a processor and a display: a plurality of cameras, coupled to the processor, configured to capture images in distinct spectral bands; and a hyperspectral flash array, coupled to the processor, configured to provide illumination to the distinct spectral bands. A method of implementing a mobile hyperspectral camera system is also described.

Abstract: A pedometer with a three-axis accelerometer provides reliable step counts while worn on the wrist. Three-axis accelerometer data is combined into a single combined data stream. Each positive slope region around an inflection point in the combined data stream that has positive slope, a magnitude that exceeds an amplitude threshold value and that spans a time period that exceeds a time threshold value is identified. Each negative slope region around an inflection point in the combined data stream that has negative slope, a magnitude that exceeds an amplitude threshold value and that spans a time period that exceeds a time threshold value is identified. A step count is incremented for each occurrence of an identified positive slope region that is separated by an identified negative slope region as a step.

Abstract: An embodiment of this disclosure provides a wearable device. The wearable device includes a memory configured to store a plurality of content for display, a transceiver configured to receive the plurality of content from a connected device, a display configured to display the plurality of content, and a processor coupled to the memory, the display, and the transceiver. The processor is configured to control the display to display at least some of the plurality of content in a spatially arranged format. The displayed content is on the display at a display position. The plurality of content, when shown on the connected device, is not in the spatially arranged format. The processor is also configured to receive movement information based on a movement of the wearable device. The processor is also configured to adjust the display position of the displayed content according to the movement information of the wearable device.

Abstract: A method of compensating for a movement of a device worn by a user is described. The method comprises measuring, using a first sensor, a motion of a user wearing the device; measuring, using a second sensor, a motion of the device; determining a difference in the motion of the device with respect to the motion of the user; and compensating for the difference in the motion of the device with respect to the motion of the user. An electronic device for monitoring a device worn by a user is also disclosed.

Abstract: A method of performing loop closure detection is described. The method comprises detecting a movement of a device having a camera; and adaptively disabling or enabling, using a processor of the device, a loop closure detection of the device based upon the detected movement of the device.

Abstract: An electronic device, method, and computer readable medium for accurate, low latency pose fusion architecture for SLAM are provided. The electronic device includes an IMU sensor, a camera, a display, and a processor coupled to the IMU sensor, the camera, and the display. The processor determines a vision pose in a camera coordinate based on the captured vision data; transforms the vision pose from the camera coordinate to an IMU coordinate; applies a scale factor, based on a combination of the vision pose and an IMU pose in the IMU coordinate, to the vision pose; fuses the scaled vision pose and the IMU pose into a fused pose in a temporally distributed manner; and outputs the fused pose for use with the display.

Abstract: Methods for heart rate measurement based on pulse oximetry are provided that can tolerate some degree of relative displacement of a photoplethysmograph (PPG) heart rate monitor device. In some methods, artifact compensation based on a reference signal is performed on the PPG signal data to remove artifacts in the signal that may be caused, for example, by changes in ambient light and/or motion of a person wearing the monitor device. The reference signal used for artifact compensation may be generated using an LED of a complementary wavelength to that of the LED used to generate the PPG signal, or by driving an LED at a lower current than the current applied to generate the PPG signal.

Abstract: A method for eye tracking in a head-mountable device (HMD) includes determining at least one object within a three-dimensional (3D) extended reality (XR) environment as an eye tracking calibration point and determining a 3D location of the eye tracking calibration point within the XR environment. The method also includes detecting a gaze point of a user of the HMD and comparing the detected gaze point to an area of the XR environment that includes the 3D location of the eye tracking calibration point. The method further includes, in response to determining that the user is looking at the eye tracking calibration point based on the detected gaze point being within the area, calibrating, using a processor, the HMD to correct a difference between the eye tracking calibration point and the detected gaze point.

Abstract: An electronic device, method, and computer readable medium for accurate, low latency pose fusion architecture for SLAM are provided. The electronic device includes an IMU sensor, a camera, a display, and a processor coupled to the IMU sensor, the camera, and the display. The processor determines a vision pose in a camera coordinate based on the captured vision data; transforms the vision pose from the camera coordinate to an IMU coordinate; applies a scale factor, based on a combination of the vision pose and an IMU pose in the IMU coordinate, to the vision pose; fuses the scaled vision pose and the IMU pose into a fused pose in a temporally distributed manner; and outputs the fused pose for use with the display.

Abstract: A method for eye tracking in a head-mountable device (HMD) includes determining at least one object within a three-dimensional (3D) extended reality (XR) environment as an eye tracking calibration point and determining a 3D location of the eye tracking calibration point within the XR environment. The method also includes detecting a gaze point of a user of the HMD and comparing the detected gaze point to an area of the XR environment that includes the 3D location of the eye tracking calibration point. The method further includes, in response to determining that the user is looking at the eye tracking calibration point based on the detected gaze point being within the area, calibrating, using a processor, the HMD to correct a difference between the eye tracking calibration point and the detected gaze point.

Abstract: A method of implementing a user interface on a mobile device is described. The method comprises learning user preference and context information; storing user preferences associated with the user-centric interface on at least one of the device or a secure server; determining and updating the context information and the user preferences on at least one of the device or a secure server.

Abstract: A method of performing loop closure detection is described. The method comprises detecting a movement of a device having a camera; and adaptively disabling or enabling, using a processor of the device, a loop closure detection of the device based upon the detected movement of the device.

Abstract: A method of compensating for a movement of a device worn by a user is described. The method comprises measuring, using a first sensor, a motion of a user wearing the device; measuring, using a second sensor, a motion of the device; determining a difference in the motion of the device with respect to the motion of the user; and compensating for the difference in the motion of the device with respect to the motion of the user. An electronic device for monitoring a device worn by a user is also disclosed.

Abstract: A method, apparatus, and computer readable medium for interactive cinemagrams. The method includes displaying a still frame of a cinemagram on a display of an electronic device, the cinemagram having an animated portion. The method also includes after the displaying, identifying occurrence of a triggering event based on an input from one or more sensors of the electronic device. Additionally, the method includes initiating animation of the animated portion of the cinemagram in response to identifying the occurrence of the triggering event. The method may also include generating the image as a cinemagram by identifying a reference frame from a plurality of frames and an object in the reference frame, segmenting the object from the reference frame, tracking the object across multiple of the frames, determining whether a portion of the reference frame lacks pixel information during motion of the object, and identifying pixel information to add to the portion.

Abstract: One embodiment provides a method comprising analyzing one or more frames of a piece of content to determine a context of the one or more frames, determining a product to advertise in the piece of content based on the context, and augmenting the piece of content with a product placement for the product. The product placement appears to occur naturally in the piece of content.

Abstract: A method, an electronic device and a non-transitory computer readable medium for are provided. The method includes capturing a first eye and a second eye. The method also includes identifying a first position of the first eye and a second position the second eye. Additionally, the method includes staggering the capture of the first eye and the second eye, wherein the first eye is captured prior to capturing the second eye. The method also includes identifying the first gaze direction with respect to a display. The method further includes mapping the second gaze direction of the second eye based on the identified first gaze direction, prior to capturing the second eye.

Abstract: A method, an electronic device and a non-transitory computer readable medium for are provided. The method includes capturing a first eye and a second eye. The method also includes identifying a first position of the first eye and a second position the second eye. Additionally, the method includes staggering the capture of the first eye and the second eye, wherein the first eye is captured prior to capturing the second eye. The method also includes identifying the first gaze direction with respect to a display. The method further includes mapping the second gaze direction of the second eye based on the identified first gaze direction, prior to capturing the second eye.

Abstract: A method for ultrasound based heart rate detection in a heart rate monitoring system is provided that includes receiving a demodulated Doppler ultrasound signal, applying a bandpass filter to the demodulated Doppler ultrasound signal to remove a direct current (DC) component and out-of-band noise, wherein a filtered demodulated Doppler ultrasound signal is generated, rectifying the filtered demodulated Doppler ultrasound signal to generate a rectified filtered demodulated Doppler ultrasound signal, applying a low-pass filter to the rectified filtered demodulated Doppler ultrasound signal to filter out undesired components to leave a resulting signal corresponding to power shift due to heart rate, detecting peaks in the resulting signal, and computing a heart rate based on the detected peaks.

Abstract: A method and apparatus for monitoring heart rate. The method includes receiving a digital heart monitoring signal, determining the integrity of said signal with a “hand detect” signal that confirms electrical connection to the subject, dividing the digital heart monitoring signal into at least one frame, generating a folded correlation value for the center sample in the at least one frame, identify the number of peaks folded correlation values based on amplitude and distance parameters of the digital heart monitoring signal in the at least one frame, removing false peaks and collecting peaks corresponding to a length of time, determining the heart rate based on the identified peaks wherein the identified peaks relate to a minimum distance between valid heart beat peaks based on a heart rate estimate, computing the weighted average of heart rate value based on the number of previous heart rate values.

Abstract: A method, apparatus, and computer readable medium for interactive cinemagrams. The method includes displaying a still frame of a cinemagram on a display of an electronic device, the cinemagram having an animated portion. The method also includes after the displaying, identifying occurrence of a triggering event based on an input from one or more sensors of the electronic device. Additionally, the method includes initiating animation of the animated portion of the cinemagram in response to identifying the occurrence of the triggering event. The method may also include generating the image as a cinemagram by identifying a reference frame from a plurality of frames and an object in the reference frame, segmenting the object from the reference frame, tracking the object across multiple of the frames, determining whether a portion of the reference frame lacks pixel information during motion of the object, and identifying pixel information to add to the portion.