Abstract: Systems, apparatuses, devices and methods for body pose tracking are provided that are simple, inexpensive, flexible, accurate and robust. One body pose tracking system includes a mobile device, such as a smartphone, and active or passive marker bands. Images and depth information captured by the smartphone may be analyzed using an Inverse Kinematic (IK) model, and, in certain cases, the IK model solution may be augmented by machine learning. Other body pose tracking systems include an augmented-reality/virtual-reality (AR/VR) head-mounted-display (HMD) and/or AR/VR glasses rather than a smartphone. An AR/VR HMD device may include a depth sensor and multiple environment-facing cameras.

Abstract: A computer-implemented method for an augmented-reality system is provided. The computer-implemented method comprises obtaining sensed data, representing an environment in which the AR system is located, determining that the AR system is in a location associated with a first authority characteristic, and controlling access to the sensed data for one or more applications operating in the AR system. Each of the one or more applications is associated with a respective authority characteristic. Controlling access to the sensed data for a said application is performed in dependence on the first authority characteristic and a respective authority characteristic associated with the said application. An AR system comprising one or more sensors, storage for storing sensed data, one or more application modules, and one or more processors arranged to perform the computer-implemented method is provided.

Abstract: When processing regions of interest in frames in a data processing system that can execute a plurality of neural networks that are each configured to more optimally process a region of interest of a respective size, a region of interest is first identified within a frame, the size of the region of interest is determined, and one of the plurality of available neural networks is selected to use to process the region of interest based on the determined size. The region of interest is scaled to produce a scaled version of the region of interest, where the scaling is determined based on the selected neural network. The scaled version of the region of interest is then processed using the selected neural network.

Abstract: Systems, apparatuses, devices and methods for body pose tracking are provided that are simple, inexpensive, flexible, accurate and robust. One body pose tracking system includes a mobile device, such as a smartphone, and active or passive marker bands. Images and depth information captured by the smartphone may be analyzed using an Inverse Kinematic (IK) model, and, in certain cases, the IK model solution may be augmented by machine learning. Other body pose tracking systems include an augmented-reality/virtual-reality (AR/VR) head-mounted-display (HMD) and/or AR/VR glasses rather than a smartphone. An AR/VR HMD device may include a depth sensor and multiple environment-facing cameras.

Abstract: An AR system is provided, the AR system including one or more sensors, storage, one or more communications modules, and one or more processors. The one or more sensors generate sensed data representing at least part of an environment in which the AR system is located. The one or more communications modules transmit localization data to be used in determining the location and orientation of the AR system. The one or more processors are arranged to obtain sensed data representing an environment in which the AR system is located, process the sensed data to identify a first portion of the sensed data which represents redundant information, derive localization data, wherein the localization data is derived from the sensed data and the first portion is obscured during the derivation of the localization data, and transmit at least a portion of the localization data using the one or more communication modules.

Abstract: A system for estimating a current camera pose corresponding to a current point in time using a previous camera pose corresponding to a previous point in time, of a camera configured to generate a sequence of image frames. The system performs operations, including: generating, using one or more neural networks, a neural network pose prediction for the current image frame; and adjusting a previous camera pose using inertial measurement unit data representing a motion of the camera between the previous point in time and the current point in time, to provide an inertial measurement unit pose prediction for the current point in time. The inertial measurement unit pose prediction, and the neural network pose prediction are combined in order to estimate the current camera pose.

Abstract: A method and apparatus for measuring depth using a time-of-flight (ToF) depth sensor is described. The apparatus includes an emitter configured to emit a signal towards a scene comprising one or more regions with light or sound, this emitter being controllable to adjust at least one of an intensity and a modulation frequency of the signal output from the emitter. The apparatus also includes a signal sensor, configured to detect an intensity of the signal from the emitter that has been reflected by the scene. A controller is configured to receive context information about the scene for depth capture by the time-of-flight depth sensor and to adjust at least one of the intensity and modulation frequency of the signal output by the emitter in dependence on the context information.

Abstract: A computer-implemented method for an augmented-reality system is provided. The computer-implemented method comprises obtaining sensed data, representing an environment in which the AR system is located, determining that the AR system is in a location associated with a first authority characteristic, and controlling access to the sensed data for one or more applications operating in the AR system. Each of the one or more applications is associated with a respective authority characteristic. Controlling access to the sensed data for a said application is performed in dependence on the first authority characteristic and a respective authority characteristic associated with the said application. An AR system comprising one or more sensors, storage for storing sensed data, one or more application modules, and one or more processors arranged to perform the computer-implemented method is provided.

Abstract: A system for estimating a current camera pose corresponding to a current point in time using a previous camera pose corresponding to a previous point in time, of a camera configured to generate a sequence of image frames. The system performs operations, including: generating, using one or more neural networks, a neural network pose prediction for the current image frame; and adjusting a previous camera pose using inertial measurement unit data representing a motion of the camera between the previous point in time and the current point in time, to provide an inertial measurement unit pose prediction for the current point in time. The inertial measurement unit pose prediction, and the neural network pose prediction are combined in order to estimate the current camera pose.

Abstract: An AR system is provided, the AR system including one or more sensors, storage, one or more communications modules, and one or more processors. The one or more sensors generate sensed data representing at least part of an environment in which the AR system is located. The one or more communications modules transmit localization data to be used in determining the location and orientation of the AR system. The one or more processors are arranged to obtain sensed data representing an environment in which the AR system is located, process the sensed data to identify a first portion of the sensed data which represents redundant information, derive localization data, wherein the localization data is derived from the sensed data and the first portion is obscured during the derivation of the localization data, and transmit at least a portion of the localization data using the one or more communication modules.