An augmented reality (AR) device can be configured to generate a virtual representation of a user's physical environment. The AR device can capture images of the user's physical environment to generate a mesh map. The AR device can project graphics at designated locations on a virtual bounding box to guide the user to capture images of the user's physical environment. The AR device can provide visual, audible, or haptic guidance to direct the user of the AR device to look toward waypoints to generate the mesh map of the user's environment.

A method of recognizing gestures of a person from at least one image from a monocular camera, e.g. a vehicle camera, includes comp the steps: a) detecting key points of the person in the at least one image, b) connecting the key points to form a skeleton-like representation of body parts of the person, wherein the skeleton-like representation represents a relative position and a relative orientation of the respective body parts of the person, c) recognizing a gesture of the person from the skeleton-like representation of the person, and d) outputting a signal indicating the gesture.

The technology described herein obfuscates image content using a local neural network and a remote neural network. The local network runs on a local computer system and a remote classifier runs in a remote computing system. Together, the local network and the remote classifier are able to classify images, while the image never leaves the local computer system. In aspects of the technology, the local network receives a local image and creates a transformed object. The transformed object may be generated by processing the image with a local neural network to generate a multidimensional array and then randomly shuffling data locations within a multidimensional array. The transformed object is communicated to the remote classifier in the remote computing system for classification. The remote classifier may not have the seed used to deterministically scramble the spatial arrangement of data within the multidimensional array.

A device and method for remotely controlling an unmanned aerial vehicle based on reinforcement learning are disclosed. An embodiment provides a device for remotely controlling an unmanned aerial vehicle based on reinforcement learning, where the device includes a processor and a memory connected to the processor, and the memory includes program instructions that can be executed by the processor to determine an inclination direction corresponding to the hand pose of a user, the movement direction of the hand, and the angle in the inclination direction based on sensing data associated with the pose of the hand or the movement of the hand acquired by way of at least one sensor, and determine one of a movement direction, a movement speed, a mode change, a figural trajectory, and a scale of the figural trajectory of the unmanned aerial vehicle according to the determined inclination direction, movement direction, and angle.

Intelligent systems are disclosed that respond to user intent and desires based upon activity that may or may not be expressly directed at the intelligent system. In some embodiments, the intelligent system acquires a depth image of a scene surrounding the system. A scene geometry may be extracted from the depth image and elements of the scene may be monitored. In certain embodiments, user activity in the scene is monitored and analyzed to infer user desires or intent with respect to the system. The interpretation of the user's intent as well as the system's response may be affected by the scene geometry surrounding the user and/or the system. In some embodiments, techniques and systems are disclosed for interpreting express user communication, e.g., expressed through hand gesture movements. In some embodiments, such gesture movements may be interpreted based on real-time depth information obtained from, e.g., optical or non-optical type depth sensors.

A user identification device according to a disclosed embodiment includes a transmitter for scattering radio-frequency (RF) signals into tissues of a body part of a user, a receiver for receiving the RF signals having passed through the tissues of the body part of the user, a memory for storing parameters of a trained classification algorithm, and a processor for identifying the user by analyzing the received RF signals based on the trained classification algorithm by using the parameters of the trained classification algorithm in response to receiving the RF signals through the receiver.

This disclosure provides a method and a system for detecting and recognizing a target object in a real-time video. The method includes: determining whether a target object recognition result R.sub.X-1 of a previous frame of image of a current frame of image is the same as a target object recognition result R.sub.X-2 of a previous frame of image of the previous frame of image; performing target object position detection in the current frame of image by using a first-stage neural network to obtain a position range C.sub.X of a target object in the current frame of image when the two recognition results R.sub.X-1 and R.sub.X-2 are different; or determining a position range C.sub.X of a target object in the current frame of image according to a position range C.sub.X-1 of the target object in the previous frame of image when the two recognition results R.sub.X-1 and R.sub.X-2 are the same; and performing target object recognition in the current frame of image according to the position range C.sub.X by using a second-stage neural network. Therefore, the operating frequency of the first-stage neural network used for position detection is reduced, the recognition speed is accelerated, and the usage of CPU and internal memory resources is reduced.

The technology disclosed herein includes a controller or device that provides multi-dimensional hand interaction with the digital world by delivering physical sensations to the palm and the fingertips. The device translates motion from the hand and fingers to control of a computer device, while simultaneously receiving signals to display haptic sensations. The device is “controller-held” around a user's hand, holding onto hand anatomy at key locations. In some embodiments, the device has one-handed engagement and disengagement. In some embodiments, the device may be used as a game controller, incorporating WebVR electronics and software, wireless communication, power-harvesting electronics, inertial measurements unit electronics including additional inputs for camera-based IMU supplementation, battery recharging electronic and internal communication protocol support electronics. In some embodiments, the device may be used in non-gaming environments, and include additional electronics that support universal remote controller components, IoT compatibility, and compatibility for wireless charging.

The present invention provides a measurement program selection assisting apparatus capable of visually confirming whether a selected measurement program is suitable for an object to be measured. One aspect of the present invention is a measurement program selection assisting apparatus comprising: a measurement program database storing a measurement program related to measurement of an object and superimposed display information corresponding to a three-dimensional shape of the object in association with each other; a display unit capable of displaying information defined in a virtual space superimposed on the real space; and a display control unit for acquiring the superimposed display information corresponding to a selected measurement program from the measurement program database and displaying the acquired superimposed display information in a mixed reality on the display unit

Systems, methods, and computer-readable media herein provide for real-time manipulation and animation of 3D rigged virtual models to generate sign language translation. Source video and audio data associated with content is provided to a neural network to determine choreographic actions that may be used to modify and animate the articulation control points of a 3D model within a 3D space. The animated 3D virtual model may be presented in relation to the source content to provide sign language translation of the source content.