Microsoft Technology Licensing, LLC

Kenneth Liam Kiemele

Christian Michael Sadak

John Benjamin Hesketh

Jeffrey Sipko

Donna Katherine Long

Bryant Daniel Hawthorne

Michael Robert Thomas

Aaron Burns

Adolfo Hernandez Santisteban

Kendall Clark York

Charlene Mary Jeune

Priya Ganadas

Evan Lewis Jones

LaSean Tee Smith

Stephen G Latta

Christian Klein

Alexandre Da Veiga

Aaron Daniel Krauss

Janet Lynn Schneider

Gregg Robert Wygonik

Thomas Salter

Jamie R Cabaccang

Roger Sebastian Sylvan

Sophors Khut

Anthony Ernst

Scott Christopher Speirs

Ricardo Arturo Espinoza Reyes

Charles W Lapp, Iii

Jennifer Jean Choi

Arthur Charles Tomlin

Andrew Austin Jackson

Michelle Tze Hiang Chua

Nikolai Michael Faaland

Roger Sebastian Kevin Sylvan

Mario Emmanuel Maltezos

James Lewis Nance

Donna K Long

Jeffrey R Sipko

Aaron Mackay Burns

John B Hesketh

Lasean T Smith

Techniques for generating a machine learning model to detect event instances from physical sensor data, including applying a first machine learning model to first sensor data from a first physical sensor at a location to detect an event instance, determining that a performance metric for use of the first machine learning model is not within an expected parameter, obtaining second sensor data from a second physical sensor during a period of time at the same location as the first physical sensor, obtaining third sensor data from the first physical sensor during the period of time, generating location-specific training data by selecting portions of the third sensor data based on training event instances detected using the second sensor data, training a second ML model using the location-specific training data, and applying the second ML model instead of the first ML model for detecting event instances.

Automated localized machine learning training

A computer system is provided that includes a server configured to store a plurality of location accounts, each location account being associated with a physical space at a recorded geospatial location. The plurality of location accounts utilize shared data definitions of a physical space parameter. Each physical space is equipped with a corresponding on-premise sensor configured to detect measured values for the physical space parameter over time and send to the server a data stream indicating the measured values. The computer system further includes a network portal, via which an authorized user for a location account can selectively choose whether to share the measured values or a summary thereof with other location accounts via the network portal.

Sharing measured values of physical space parameters

Optimizations are provided for facilitating an improved transition between a real-world environment and a virtual reality environment. Initially, use of a HMD is detected and one or more real-world physical objects within a threshold proximity to the HMD are identified. Subsequently, a replicated environment, which includes virtual representations of the real-world physical object(s), is obtained and rendered in a virtual reality display. The replicated environment is transitioned out of view and a VR environment is subsequently rendered in the virtual reality display. In some instances, rendering of virtual representations of real-world physical objects into the VR environment occurs is response to detected triggering event.

Transitioning into a VR environment and warning HMD users of real-world physical obstacles

Methods and devices for providing a haptic responses to a haptic feedback device may include receiving, by an application providing a virtual environment executing on a computer device, physical movement input based at least on movement of the haptic feedback device that corresponds to a virtual movement interaction with a virtual object in the virtual environment. The methods and devices may include accessing a haptic signature associated with the virtual object. The methods and devices may include determining a haptic response based at least upon the haptic signature to identify the virtual object through the haptic response. The methods and devices may include transmitting the haptic response to the haptic feedback device.

Natural interactions with virtual objects and data through touch

A device for removal of personally identifiable data receives monitoring data acquired by a sensor. The monitoring data including personally identifiable data relating to one or more individuals being monitored. The system processes the acquired monitoring data to remove the personally identifiable data by at least one of abstraction or redaction while the monitoring data is located on the device. The processed monitoring data having the personally identifiable data removed can thereby be transmitted external to the device with reduced security risk.

Removing personally identifiable data before transmission from a device

A wearable device is configured with a one-dimensional depth sensor (e.g., a LIDAR system) that scans a physical environment, in which the wearable device and depth sensor generate a point cloud structure using scanned points of the physical environment to develop blueprints for a negative space of the environment. The negative space includes permanent structures (e.g., walls and floors), in which the blueprints distinguish permanent structures from temporary objects. The depth sensor is affixed in a static position on the wearable device and passively scans a room according to the gaze direction of the user. Over a period of days, weeks, months, or years the blueprint continues to supplement the point cloud structure and update points therein. Thus, as the user continues to navigate the physical environment, over time, the point cloud data structure develops an accurate blueprint of the environment.

Using a one-dimensional ray sensor to map an environment

The present disclosure provides apparatus and methods for automated tracking and counting of objects in a set of image frames using a resource-constrained device based on analysis of a selected subset of image frames, and based on selectively timing when resource-intensive operations are performed.

Apparatus and methods of automated tracking and counting of objects on a resource-constrained device

Examples are disclosed herein that relate to receiving virtual reality input. An example provides a head-mounted display device comprising a sensor system, a display, a logic machine, and a storage machine holding instructions executable by the logic machine. The instructions are executable to execute a 3D virtual reality experience on the head-mounted display device, track, via the sensor system, a touch-sensitive input device, render, on the display, in a 3D location in the 3D virtual reality experience based on the tracking of the touch-sensitive input device, a user interface, receive, via a touch sensor of the touch-sensitive input device, a user input, and, in response to receiving the user input, control the 3D virtual reality experience to thereby vary visual content being rendered on the display.

Virtual reality input

Examples are disclosed that relate to refining virtual mesh models through physical contacts. For example, a hand-mounted mobile device, such as a wearable glove, may be used to create and/or emphasize specific points within a virtual mesh model of a physical environment. An indication of physical contact of an interface of the mobile device with a physical object may be obtained via a touch sensor of the mobile device. A location and/or an orientation of the interface of the mobile device during the physical contact with the physical object may be identified based on sensor data obtained from one or more positioning sensors. Location data indicating the location may be stored in a data storage device from which the location data may be referenced. In an example, refinement of a virtual mesh model of a physical environment containing the physical object may be prioritized based on the location data.

Refining virtual mesh models through physical contacts

Examples are disclosed that relate to devices and methods for sharing geo-located information between different devices. In one example, a method comprises receiving the geo-located information from a first user device having a first data type compatible with a first output component of the device, receiving first sensor data from the first device, determining a location of the geo-located information within a coordinate system in a physical environment, determining that a second user device is located in the physical environment, determining that the second device does not comprise an output component that is compatible with the first data type, transforming the geo-located information into a second data type compatible with a second output component of the second device, determining that the second device is proximate to the location of the geo-located information, and sending the geo-located information to the second device for output by the second output component.

Sharing geo-located information

Techniques are described herein that are capable of making a state-based determination of information to be displayed on a screen region of a hinge that is coupled to other screen regions. For instance, a state of a hinge that is coupled between a first screen region and a second screen region may be determined. Information that is to be displayed on a third screen region that is provided on the hinge may be determine based at least in part on the state of the hinge.

Device having a screen region on a hinge coupled between other screen regions

A computing system is provided, including a plurality of display devices including at least a first display device and a second display device. The computing system may further include one or more sensors configured to detect a first positional state of the first display device relative to the second display device and at least one user. The first positional state may include an angular orientation of the first display device relative to the second display device. The computing system may further include a processor configured to receive the first positional state from the one or more sensors. The processor may be further configured to generate first graphical content based at least in part on the first positional state. The processor may be further configured to transmit the first graphical content for display at the first display device.

Displaying content based on positional state

To address issues of capturing and processing images, a mobile computing device is provided. The mobile computing device may include a two-part housing coupled by a hinge, with first and second parts that include first and second displays, respectively. The hinge may permit the displays to rotate throughout a plurality of angular orientations. The mobile computing device may include one or more sensor devices, processor, first camera, and second camera mounted in the housing. The one or more sensor devices may be configured to measure the relative angular displacement of the housing, and the processor may be configured to process images captured by the first and second cameras according to a selected function based upon the relative angular displacement measured by the one or more sensor devices.

Image capture using a hinged device with multiple cameras

Growing community of inventors

Redmond, WA, United States of America

Kenneth Liam Kiemele