Hewlett-Packard Development Company, L.p.

Madhu Sudan Athreya

Sunil Bharitkar

William James Allen

Andrew Arthur Hunter

Will Allen

Carlos Haas

Qian Lin

Helen Ann Holder

Richard F Sweet

Srikanth Kuthuru

David Murphy

Cheng I Huang

Robert C Brooks

Kent E Biggs

Alexander Wayne Clark

Mary G Baker

Carlos Haas Costa

Wensen Liu

Eric Faggin

Caio Northfleet

M Anthony Lewis

Ticky Thakkar

Seethal Paluri

Christian Makaya

Thiago Jose Da Silva

Systems and methods are described herein to orchestrate the execution of an application, such as a machine learning or artificial intelligence application, using distributed compute clusters with heterogeneous compute resources. A discovery subsystem may identify the different compute resources of each compute cluster. The application is divided into a plurality of workloads with each workload associated with resource demands corresponding to the compute resources of one of the compute clusters. Adaptive modeling allows for hyperparameters to be defined for each workload based on the compute resources associated with the compute cluster to which each respective workload is assigned and the associated dataset.

Machine learning workload orchestration in heterogeneous clusters

Examples for global motion suppression in an event-driven camera are described herein. In some examples, global motion of an event-driven camera is detected based on a plurality of pixels of an event-driven image sensor detecting events. The global motion may be suppressed by event-driven image sensor circuitry in response to detecting the global motion.

Global motion suppression in an event-driven camera

Acoustic echo cancellation for a video conference system is described. A location of a person in a room can be determined. An audio signal received from the location of the person can be captured using beamforming. An acoustic echo cancellation parameter can be determined based in part on the audio signal captured from the location of the person. Acoustic echo cancellation can be performed on the audio signal using the acoustic echo cancellation parameter.

Acoustic echo cancellation

An apparatus includes a support, a first camera, and second camera, and a processor. The support is configured to be mounted to a head of a user. The first camera is mounted on the support and positioned to capture a first image of a face of the user. The second camera is mounted on the support and positioned to capture a second image of the face of the user that is non-overlapping with the first image. The processor is mounted to the support and programmed to stitch the first image and the second image together to construct an image of the face of the user.

Constructing images of users' faces by stitching non-overlapping images

An example device includes a main display panel that includes a main array of pixels and an opening within the main array of pixels. The example device further includes a beam splitter positioned to communicate light through the opening within the main array of pixels, a sensor positioned with respect to the beam splitter to capture light incident on the opening within the main array of pixels, and a subarray including a pixel. The subarray is positioned with respect to the beam splitter to output light through the opening within the main array of pixels.

Displays with pixels coupled by beam splitters

Examples disclosed herein provide the ability for a computing device to adjust settings on a computing device. In one example method, the computing device captures, via a first sensor of a computing device, images of an environment that the computing device is currently in, and detects objects in the environment as captured by the images. As an example, the computing device determines a location of the environment based on contextual data gathered from the detected objects and adjusts a setting on the computing device based on the determined location.

Adjusting settings on computing devices based on location

A computer device including an integrated input device is provided. The integrated input device includes a positive disconnect system including a display of an open connection to the integrated input device when the integrated input device is deactivated. The open connection comprises a visible metal trace on a line coupling the integrated input device to the computer device.

Positive disconnection of integrated input devices

In some examples, adaptive speech intelligibility control for speech privacy may include determining, based on background noise at a near-end of a speaker, a noise estimate associated with speech emitted from the speaker, and comparing, by using a specified factor, the noise estimate to a speech level estimate for the speech emitted from the speaker. Adaptive speech intelligibility control for speech privacy may further include determining, based on the comparison, a gain value to be applied to the speaker to produce the speech at a specified level to maintain on-axis intelligibility with respect to the speaker, and applying the gain value to the speaker.

Adaptive speech intelligibility control for speech privacy

A communication system may include, in an example, a first computing device communicatively coupled, via a network, to at least a second computing device maintained at a geographically distinct location than the first computing device; the first computing device including: an array of audio output devices and a processor to receive transmitted speech data and metadata describing an estimated direction of arrival (DOA) of speech from a plurality of speakers at an array of microphones at the second computing device and render audio at the array of audio output devices associated with the first computing device by eliminating spatial collision during rendering; said spatial collision arising due to the low angular separation of the estimated DOA of a plurality of speakers.

Eliminating spatial collisions due to estimated directions of arrival of speech

A method, an apparatus and a machine-readable medium are disclosed. The method relates to operating a user interface. The method may include obtaining, using a sensor associated with a first processing apparatus, data indicative of a pose of an control element and a gesture performed by the control element; delivering the data indicative of the pose and the gesture from the first processing apparatus to a second processing apparatus, the second processing apparatus associated with a computing device for displaying a user interface, wherein the second processing apparatus is remote from the first processing apparatus; generating, based on the data indicative of the pose, a representation of the control element to be presented on the user interface; presenting the representation of the control element on the user interface; determining, using the second processing apparatus, an operation corresponding to the performed gesture; and performing the operation in respect of the user interface on the computing device.

Operating user interfaces

In example implementations, a method is provided. The method may be executed by a processor. The method includes receiving a reflected image of a mirrored display. At least one optimal display region is identified in the mirrored display around a main subject in the reflected image based on additional reflected subjects in the reflected image. A content is analyzed to determine an arrangement of the content in the at least one optimal display region. The content that is displayed is arranged in the at least one optimal display region.

Content arrangements on mirrored displays

In an example, an augmented reality display system includes a reflective surface, a depth scanner and processing apparatus comprising an image processor and an image generation engine. The depth scanner may be to scan the reflective surface and a subject via the reflective surface to acquire depth data. The image processor may be to determine, based on the depth data, a viewpoint for an augmentation of a reflected image. The image generation engine may be to generate the augmentation for display on the reflective surface.

Augmented reality display

An example non-transitory computer-readable medium includes instructions. When executed by a processor, the instructions cause the processor to split a video frame into a first frame including blocks classified as natural and a second frame including blocks classified as artificial. The instructions also cause the processor to compress the first frame with a first compression technique. The instructions also cause the processor to compress the second frame with a second compression technique.

Video compression

One example of a video monitoring system includes a frame acquisition subsystem, a stage gate motion detection subsystem, a person detection subsystem, a face recognition subsystem, and an alert emission subsystem. The frame acquisition subsystem extracts frames from an input video. The stage gate motion detection subsystem separates background motion from foreground motion within frames. The person detection subsystem detects people including faces and bodies within the foreground motion. The face recognition subsystem matches detected faces to previously registered users. The alert emission subsystem provides alerts based on events detected by the stage gate motion subsystem, the person detection subsystem, and the face recognition subsystem.

Growing community of inventors

Palo Alto, CA, United States of America

Madhu Sudan Athreya