Abstract: Described are multiple cameras in a conference room, each pointed in a different direction. A primary camera includes a microphone array to perform sound source localization (SSL). The SSL is used in combination with a video image to identify the speaker from among multiple individuals that appear in the video image. Pose information of the speaker is developed. Pose information of each individual identified in each other camera is developed. The speaker pose information is compared to the pose information of the individuals from the other cameras. The best match for each other camera is selected as the speaker in that camera. The speaker views of each camera are compared to determine the speaker view with the most frontal view of the speaker. That camera is selected to provide the video for provision to the far end.

Abstract: Described are multiple cameras in a conference room, each pointed in a different direction. A primary camera includes a microphone array to perform sound source localization (SSL). The SSL is used in combination with a video image to identify the speaker from among multiple individuals that appear in the video image. Pose information of the speaker is developed. Pose information of each individual identified in each other camera is developed. The speaker pose information is compared to the pose information of the individuals from the other cameras. The best match for each other camera is selected as the speaker in that camera. The speaker views of each camera are compared to determine the speaker view with the most frontal view of the speaker. That camera is selected to provide the video for provision to the far end.

Abstract: A method including generating, by applying a three-dimensional pose estimation model to an original image generated by a camera, estimated three-dimensional poses for people in the original image. The estimated three-dimensional poses include distances from the camera. The method further includes determining, using the distances, a far people subset of the people. Each person of the far people subset corresponds to a distance from the camera exceeding a threshold distance. The method further includes, deriving, for the far people subset, regions of interest, upscaling a region of interest for a person of the far people subset to generate an upscaled region of interest, and generating, from the original image and the upscaled region of interest, an enhanced image.

Abstract: Distributed machine learning inference includes acquiring, by an input device, an input frame, executing, by an embedded processor of the input device, a model feature extractor on the input frame to obtain extracted features of the input frame, and transmitting the extracted features from the input device to a processing device. The processing device executes a model feature aggregator to process the plurality of extracted features and obtain a model result.

Abstract: A system for preventing private image data captured at an endpoint from being shared during a videoconference is provided. A user can select three-dimensional regions which will not be seen during a videoconference while areas in front of the designated regions remain viewable.

Abstract: Multiple cameras in a conference room, each pointed in a different direction and including a microphone array to perform sound source localization (SSL). The SSL is used in combination with the video image to identify the speaker from among multiple individuals that appear in the video image. Neural network or machine learning processing is performed on the identified speaker to determine the quality of the front or facial view of the speaker. The best view of the speaker's face from the various cameras is selected to be provided to the far end. If no view is satisfactory, a default view is selected and that is provided to the far end. The use of the SSL allows selection of the proper individual from a group of individuals in the conference room, so that only the speaker's head is analyzed for the best facial view and then framed for transmission.

Abstract: Described are multiple cameras in a conference room, each pointed in a different direction. A primary camera includes a microphone array to perform sound source localization (SSL). The SSL is used in combination with a video image to identify the speaker from among multiple individuals that appear in the video image. Pose information of the speaker is developed. Pose information of each individual identified in each other camera is developed. The speaker pose information is compared to the pose information of the individuals from the other cameras. The best match for each other camera is selected as the speaker in that camera. The speaker views of each camera are compared to determine the speaker view with the most frontal view of the speaker. That camera is selected to provide the video for provision to the far end.

Abstract: Multiple cameras in a conference room, each pointed in a different direction and including a microphone array to perform sound source localization (SSL). The SSL is used in combination with the video image to identify the speaker from among multiple individuals that appear in the video image. Neural network or machine learning processing is performed on the identified speaker to determine the quality of the front or facial view of the speaker. The best view of the speaker's face from the various cameras is selected to be provided to the far end. If no view is satisfactory, a default view is selected and that is provided to the far end. The use of the SSL allows selection of the proper individual from a group of individuals in the conference room, so that only the speaker's head is analyzed for the best facial view and then framed for transmission.

Abstract: A teleconferencing system, comprising: a camera, wherein the camera is configured to capture an image data stream comprising one or more image data frames in accordance with one or more image-capture parameters; and a processor coupled to the camera, wherein the processor is configured to: receive the image data stream from the camera; determine a region of interest within an image data frame of the image data stream; identify a sub-portion of the image data frame corresponding to the region of interest; evaluate a quality of image data corresponding to the sub-portion; determine that the quality of the image data corresponding to the sub-portion is below one or more predetermined quality thresholds; update one or more of the image-capture parameters of the camera, responsive to determining that the quality of the image data corresponding to the sub-portion is below the one or more predetermined quality thresholds.

Abstract: A teleconferencing system, comprising: a camera, wherein the camera is configured to capture an image data stream comprising one or more image data frames in accordance with one or more image-capture parameters; and a processor coupled to the camera, wherein the processor is configured to: receive the image data stream from the camera; determine a region of interest within an image data frame of the image data stream; identify a sub-portion of the image data frame corresponding to the region of interest; evaluate a quality of image data corresponding to the sub-portion; determine that the quality of the image data corresponding to the sub-portion is below one or more predetermined quality thresholds; update one or more of the image-capture parameters of the camera, responsive to determining that the quality of the image data corresponding to the sub-portion is below the one or more predetermined quality thresholds.

Abstract: A rotating control device for sealing an annulus includes an outer housing, and a seal assembly disposed within the outer housing and configured to seal against a rotating tubular member extending axially through a throughbore of the outer housing, wherein the seal assembly includes an inner housing, a first proximity sensor disposed along an inner surface of the outer housing, and a first sensor element disposed along an outer surface of the inner housing, wherein the first proximity sensor is configured to measure the rotational speed of the seal assembly in response to rotation of the seal assembly in the outer housing.

Abstract: At a first physical computing machine executing a plurality of virtual machines and connected to a network, one or more virtual machine metrics for each virtual machine are calculated. Each virtual machine metric represents a workload of a resource of the first physical computing machine due to the execution of a corresponding virtual machine. Additionally, one or more corresponding physical machine metrics that represent a total workload of the corresponding resource of the first physical computing machine due to the execution of the plurality of virtual machines are also calculated. Based on the one or more physical machine metrics, a determination is made that at least one of the plurality of virtual machines should be migrated to one of a plurality of other physical computing machines connected to the network. A first virtual machine is selected for migration to a selected second physical computing machine.

Abstract: At a first physical computing machine executing a plurality of virtual machines and connected to a network, one or more virtual machine metrics for each virtual machine are calculated. Each virtual machine metric represents a workload of a resource of the first physical computing machine due to the execution of a corresponding virtual machine. Additionally, one or more corresponding physical machine metrics that represent a total workload of the corresponding resource of the first physical computing machine due to the execution of the plurality of virtual machines are also calculated. Based on the one or more physical machine metrics, a determination is made that at least one of the plurality of virtual machines should be migrated to one of a plurality of other physical computing machines connected to the network. A first virtual machine is selected for migration to a selected second physical computing machine.

Abstract: In nonlinear power state transitioning, temporal intervals of inactivity in network traffic traversing a network node are determined from transport control data carried in the network traffic. An interrupt is generated that compels a deepest diminished power state from a plurality of power states in the network node. The deepest diminished power state is the deepest power state from which recovery to a completely powered state within a minimum one of the inactivity intervals is assured. Electrical energy consumption in the network node is reduced in response to the interrupt in accordance with a power management schedule.

Abstract: At a first physical computing machine executing a plurality of virtual machines and connected to a network, one or more virtual machine metrics for each virtual machine are calculated. Each virtual machine metric represents a workload of a resource of the first physical computing machine due to the execution of a corresponding virtual machine. Additionally, one or more corresponding physical machine metrics that represent a total workload of the corresponding resource of the first physical computing machine due to the execution of the plurality of virtual machines are also calculated. Based on the one or more physical machine metrics, a determination is made that at least one of the plurality of virtual machines should be migrated to one of a plurality of other physical computing machines connected to the network. A first virtual machine is selected for migration to a selected second physical computing machine.

Abstract: In nonlinear power state transitioning, temporal intervals of inactivity in network traffic traversing a network node are determined from transport control data carried in the network traffic. An interrupt is generated that compels a deepest diminished power state from a plurality of power states in the network node. The deepest diminished power state is the deepest power state from which recovery to a completely powered state within a minimum one of the inactivity intervals is assured. Electrical energy consumption in the network node is reduced in response to the interrupt in accordance with a power management schedule.

Abstract: A method of predicting behavior of a drilling assembly includes generating, by a processor, a mathematical representation of a geometry of drill bit that includes a plurality of earth contacting portions, the plurality of earth contacting portions including a plurality of cutters and one or more additional components; estimating, with a separate model for each earth contacting portion, contact with the earth formation during a drilling operation; and estimating one or more forces on the one or more earth contact portions during the drilling operation based on the estimated contact.

Abstract: At a first physical computing machine executing a plurality of virtual machines and connected to a network, one or more virtual machine metrics for each virtual machine are calculated. Each virtual machine metric represents a workload of a resource of the first physical computing machine due to the execution of a corresponding virtual machine. Additionally, one or more corresponding physical machine metrics that represent a total workload of the corresponding resource of the first physical computing machine due to the execution of the plurality of virtual machines are also calculated. Based on the one or more physical machine metrics, a determination is made that at least one of the plurality of virtual machines should be migrated to one of a plurality of other physical computing machines connected to the network. A first virtual machine is selected for migration to a selected second physical computing machine.

Abstract: A method that addresses a cross layer optimization technique for TCP in which the need to send ACK frames across wireless links is contained by using the information from the MAC layer acknowledgements is disclosed. More specifically the method significantly reduces bandwidth consumption and improves the performance of TCP on wireless networks. Furthermore, since the number of transmitted and received packets is reduced at the mobile device, the battery life of the device can be improved significantly. The proposed method can also be applied to downlink and uplink ACK frames with a slight variation between the two.