Abstract: Devices, systems and methods are disclosed for improving facial recognition and/or speaker recognition models by using results obtained from one model to assist in generating results from the other model. For example, a device may perform facial recognition for image data to identify users and may use the results of the facial recognition to assist in speaker recognition for corresponding audio data. Alternatively or additionally, the device may perform speaker recognition for audio data to identify users and may use the results of the speaker recognition to assist in facial recognition for corresponding image data. As a result, the device may identify users in video data that are not included in the facial recognition model and may identify users in audio data that are not included in the speaker recognition model. The facial recognition and/or speaker recognition models may be updated during run-time and/or offline using post-processed data.

Abstract: A video capture device may include multiple cameras that simultaneously capture video data. The video capture device and/or one or more remote computing resources may stitch the video data captured by the multiple cameras to generate stitched video data that corresponds to 360° video. The remote computing resources may apply one or more algorithms to the stitched video data to identify one or more frames that depict content that is likely to be of interest to a user. The video capture device and/or the remote computing resources may generate one or more images from the one or more frames, and may send the one or more images to the user.

Abstract: Various examples are directed to systems and methods for selecting image sensors in a multiple image sensor device. A control circuit may receive a first frame from the first image sensor and a second frame from the second image sensor. The control circuit may receive object data describing an object depicted in the first frame and may turn off the second image sensor.

Abstract: Devices, systems and methods are disclosed for improving facial recognition and/or speaker recognition models by using results obtained from one model to assist in generating results from the other model. For example, a device may perform facial recognition for image data to identify users and may use the results of the facial recognition to assist in speaker recognition for corresponding audio data. Alternatively or additionally, the device may perform speaker recognition for audio data to identify users and may use the results of the speaker recognition to assist in facial recognition for corresponding image data. As a result, the device may identify users in video data that are not included in the facial recognition model and may identify users in audio data that are not included in the speaker recognition model. The facial recognition and/or speaker recognition models may be updated during run-time and/or offline using post-processed data.

Abstract: A viewing device, such as a virtual reality headset, allows a user to view a panoramic scene captured by one or more video capture devices that may include multiple cameras that simultaneously capture 360° video data. The viewing device may display the panoramic scene in real time and change the display in response to moving the viewing device and/or changing perspectives by switching to video data being captured by a different video capture device within the environment. Moreover, multiple video capture devices located within an environment can be used to create a three-dimensional representation of the environment that allows a user to explore the three-dimensional space while viewing the environment in real time.

Abstract: Devices, systems and methods are disclosed for improving facial recognition and/or speaker recognition models by using results obtained from one model to assist in generating results from the other model. For example, a device may perform facial recognition for image data to identify users and may use the results of the facial recognition to assist in speaker recognition for corresponding audio data. Alternatively or additionally, the device may perform speaker recognition for audio data to identify users and may use the results of the speaker recognition to assist in facial recognition for corresponding image data. As a result, the device may identify users in video data that are not included in the facial recognition model and may identify users in audio data that are not included in the speaker recognition model. The facial recognition and/or speaker recognition models may be updated during run-time and/or offline using post-processed data.

Abstract: Systems and methods may be directed to de-blurring panoramic images and/or video. An image processor may receive a frame, where the frame comprises a plurality of pixel values arranged in a grid. The image processor may divide the frame into a first section and a second section. The image processor may determine a first motion kernel for the first section and apply the first motion kernel to the first section. The image processor may also determine a second motion kernel for the second section and apply the second motion kernel to the second section.

Abstract: The hand which a user is using to hold an electronic device can be determined by analyzing data captured by one or more motion sensors on the device. The curvature to the motion can be indicative of handedness, and processing motion features using a classifier algorithm can enable the determination of handedness with a corresponding confidence. In some embodiments, motion data is collected over a monitoring window, and handedness values are accepted when the handedness value remains the same with at least a minimum confidence for at least a minimum number of window periods. A determination of handedness enables an operating system and/or applications executing on the device to adjust one or more operational or interface aspects in order to make it easier for the user to operate the device using the hand currently holding the device.

Abstract: A video capture device may include multiple cameras that simultaneously capture video data. The video capture device and/or one or more remote computing resources may stitch the video data captured by the multiple cameras to generate stitched video data that corresponds to 360° video. The remote computing resources may apply one or more algorithms to the stitched video data to adjust the color characteristics of the stitched video data, such as lighting, exposure, white balance contrast, and saturation. The remote computing resources may further smooth the transition between the video data captured by the multiple cameras to reduce artifacts such as abrupt changes in color as a result of the individual cameras of the video capture device having different video capture settings. The video capture device and/or the remote computing resources may generate a panoramic video that may include up to a 360° field of view.

Abstract: Devices, systems and methods are disclosed for identifying content in video data and creating content-based zooming and panning effects to emphasize the content. Contents may be detected and analyzed in the video data using computer vision, machine learning algorithms or specified through a user interface. Panning and zooming controls may be associated with the contents, panning or zooming based on a location and size of content within the video data. The device may determine a number of pixels associated with content and may frame the content to be a certain percentage of the edited video data, such as a close-up shot where a subject is displayed as 50% of the viewing frame. The device may identify an event of interest, may determine multiple frames associated with the event of interest and may pan and zoom between the multiple frames based on a size/location of the content within the multiple frames.

Abstract: A tracking architecture is provided that enables data for gestures and head positions to be provided to both native and non-native clients on a computing device. A pipeline component can obtain the raw image data and sensor data and synchronize that data to be processed to determine, for example, location and/or motion data that may correspond to device input. The data can be processed by separate components, such as an event publisher and an event provider, each capable of filtering the location, motion, and/or raw sensor data to generate a set of event data. The event data then can be published to registered listeners or provided in response to polling requests. Head coordinates, gesture data, and other such information can be passed through one or more interface layers enabling the data to be processed by a non-native client on the device.

Abstract: Devices, systems and methods are disclosed for identifying content in video data and creating content-based zooming and panning effects to emphasize the content. Contents may be detected and analyzed in the video data using computer vision, machine learning algorithms or specified through a user interface. Panning and zooming controls may be associated with the contents, panning or zooming based on a location and size of content within the video data. The device may determine a number of pixels associated with content and may frame the content to be a certain percentage of the edited video data, such as a close-up shot where a subject is displayed as 50% of the viewing frame. The device may identify an event of interest, may determine multiple frames associated with the event of interest and may pan and zoom between the multiple frames based on a size/location of the content within the multiple frames.

Abstract: A computing device can be controlled based on changes in the angle of a user's head with respect to the device, such as due to the user tilting the device and/or the user tilting his head with respect to the device. Such control based on the angle of the user's head can be achieved even when the user is operating the device “off-axis” or when the device is not orthogonal and/or not centered with respect to the user. This can be accomplished by using an elastic reference point that dynamically adjusts to a detected angle of the user's head with respect to the device. Such an approach can account for differences between when the user is changing his natural resting position and/or the resting position of the device and when the user is intending to perform a gesture based on the angle of the user's head relative to the device.

Abstract: A device may recognize a tilt gesture when a device rotates about an axis and then back again. The gesture may be recognized using a state machine. Recognition of the gesture may be performed based on a context of a device, where the specific movement of the device during a tilt gesture may change based on the context. The tilt gesture may be confirmed using a classifier trained on features describing the gesture and the context.

Abstract: A tracking architecture is provided that enables data for gestures and head positions to be provided to both native and non-native clients on a computing device. A pipeline component can obtain the raw image data and sensor data and synchronize that data to be processed to determine, for example, location and/or motion data that may correspond to device input. The data can be processed by separate components, such as an event publisher and an event provider, each capable of filtering the location, motion, and/or raw sensor data to generate a set of event data. The event data then can be published to registered listeners or provided in response to polling requests. Head coordinates, gesture data, and other such information can be passed through one or more interface layers enabling the data to be processed by a non-native client on the device.