公开(公告)号：US20200279127A1

公开(公告)日：2020-09-03

申请号：US16877696

申请日：2020-05-19

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Bo Han ,  Tan Xu ,  Cheuk Yiu Ip

IPC: G06K9/46 ,  G06K9/32 ,  G06F3/01 ,  H04N13/117 ,  H04N5/232

Abstract: Aspects of the subject disclosure may include, for example, a method performed by a processing system of determining a present orientation of a display region presented at a first time on a display of a video viewer, predicting a future orientation of the display region occurring at a second time based on data collected, to obtain a predicted orientation of the display region to be presented at the second time on the display of the video viewer, identifying, based on the predicted orientation of the display region, a first group of tiles from a video frame of a panoramic video being displayed by the video viewer, wherein the first group of tiles covers the display region in the video frame at the predicted orientation, and a plurality of objects moving in the video frame from the first time to the second time, wherein each object of the plurality of objects is located in a separate spatial region of the video frame at the second time, wherein a second group of tiles collectively covers the separate spatial regions, wherein tiles in the first group of tiles and tiles in the second group of tiles are different, and facilitating wireless transmission of the first group of tiles and a second tile from the second group of tiles, for presentation at the video viewer at the second time. Other embodiments are disclosed.

公开(公告)号：US20200260126A1

公开(公告)日：2020-08-13

申请号：US16859937

申请日：2020-04-27

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Bo Han ,  Vijay Gopalakrishnan ,  Tan Xu

IPC: H04N21/218 ,  H04N19/17 ,  G06N20/20 ,  H04N19/597 ,  G06F3/0481 ,  G06F3/01

Abstract: A method for streaming a 360 degree video over a communications network, wherein the video is streamed in a plurality of chunks, includes selecting a prediction window during which to predict a field of view within the video, the field of view is expected to be visible by a viewer at a time of playback of a next chunk of the video, wherein a duration of the prediction window is based on at least one condition within the communications network, selecting a machine learning algorithm to predict the field of view based on a head movement of the viewer, wherein the machine learning algorithm is selected based on the duration of the prediction window, predicting the field of view based on the head movement of the viewer and the machine learning algorithm, identifying a tile of the next chunk that corresponds to the field of view, and downloading the tile.

公开(公告)号：US10735882B2

公开(公告)日：2020-08-04

申请号：US15993777

申请日：2018-05-31

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Bo Han ,  Manuel Briand ,  Vijay Gopalakrishnan

IPC: H04S7/00 ,  H04N21/233 ,  H04N21/218

Abstract: Aspects of the subject disclosure may include, for example, a method for spherical video streaming over a network by a processing system including a processor, the method including prefetching audio data for rendering the spherical video; determining whether there is a single source or a plurality of sources of audio in the audio data; responsive to a determination that there is only one dominant source of the audio in the audio data, prefetching video data in a field of view centered on spatial coordinates of the dominant source of audio; responsive to a determination that there is the plurality of sources of the audio in the audio data, sorting the plurality of sources of the audio according to an estimated sound source energy for each source in the plurality of sources, thereby creating a sorted list of the plurality of sources; and prefetching video data in plural fields of view centered on spatial coordinates of each audio source in the sorted list of the plurality of sources, wherein the prefetching is performed in an order corresponding to the sorted list, and wherein the prefetching occurs within an available bandwidth of the network. Other embodiments are disclosed.

公开(公告)号：US20200221149A1

公开(公告)日：2020-07-09

申请号：US16825667

申请日：2020-03-20

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Bo Han ,  Matteo Varvello ,  Vijay Gopalakrishnan

IPC: H04N21/25 ,  H04N5/232 ,  H04N21/414 ,  H04N21/2343 ,  H04N21/442 ,  H04N21/81

Abstract: Aspects of the subject disclosure may include, for example, a method including providing a video presentation to user devices. A latency related to the video presentation is determined for each device; a high-latency user device is identified having greater latency than other, low-latency devices. Field of view information is analyzed for each of the low-latency devices; based on the analyzing, a field of view of the high-latency user device is predicted. In accordance with the predicting, a predicted viewing map for the high-latency user device is generated. The video presentation for the high-latency user device is adjusted based on the predicted viewing map. Other embodiments are disclosed.

公开(公告)号：US20200210704A1

公开(公告)日：2020-07-02

申请号：US16234029

申请日：2018-12-27

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Bo Han ,  Muhammad Bilal Anwer ,  Vijay Gopalakrishnan ,  Wenxiao Zhang ,  Pan Hui

IPC: G06K9/00 ,  G06K9/62 ,  G06T7/13 ,  G06T7/246 ,  G06T7/73 ,  G06T3/40

Abstract: A processing system having at least one processor may obtain a feature set from a camera frame of a client device, perform a feature reduction of the feature set to produce a reduced feature set, generate a compressed representation from the reduced feature set, compare the compressed representation of the reduced feature set to a plurality of compressed representations of known objects stored in one or more hash tables to identify an object in the camera frame, and provide an identification of the object to the client device.

公开(公告)号：US10659190B1

公开(公告)日：2020-05-19

申请号：US16285066

申请日：2019-02-25

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Zhengye Liu ,  Xidong Wu ,  Jin Wang ,  Bo Han

IPC: G06F15/16 ,  H04L1/00 ,  H04L29/06

Abstract: Devices, computer-readable media, and methods for selecting a type of transmission for an immersive visual stream based upon a latency estimate. For instance, a processing system including at least one processor may obtain a latency estimate for an immersive visual stream, determine whether the latency estimate exceeds a latency threshold for selecting a type of transmission for the immersive visual stream, and select the type of transmission for the immersive visual stream from among a field of view restricted type of transmission and a field of view plus out of scene type of transmission based upon the determining. When the latency estimate is determined to not exceed the latency threshold, the field of view restricted type of transmission is selected. When the latency estimate is determined to exceed the latency threshold, the field of view plus out of scene type of transmission is selected.

公开(公告)号：US20200128060A1

公开(公告)日：2020-04-23

申请号：US16371287

申请日：2019-04-01

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Bo Han ,  Sassan Pejhan ,  Vijay Gopalakrishnan

IPC: H04L29/06

Abstract: Aspects of the subject disclosure may include, for example, obtaining live video content from equipment of a media content provider, determining priority content within the live video content; segmenting the live video content into a plurality of tiles according to the priority content, and transcoding the live video content according to a type of client device. Further embodiments include determining an encoding schedule for the plurality of tiles according to the priority content, encoding the plurality of tiles according to the encoding schedule, and providing the plurality of tiles to the client device. Other embodiments are disclosed.

公开(公告)号：US20190313119A1

公开(公告)日：2019-10-10

申请号：US15949797

申请日：2018-04-10

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Bo Han ,  Vijay Gopalakrishnan ,  Jackson Jarrell Pair ,  Vikash Sharma

IPC: H04N19/597 ,  H04N19/174 ,  H04N5/232 ,  H04N13/161

Abstract: Aspects of the subject disclosure may include, for example, identifying a field of view (FoV) within a first frame of a video that occupies a sub-portion of the frame. A size is determined by subdividing a portion of the video according to a tiling scenario. Tiles overlapping the FoV are detected, and an updated size is determined based on an encoded version of the tiles and compared to a reference size. Responsive to the updated size being less than the reference size, the reference size is adjusted to the updated size, the tiling scenario is adjusted according to an adjusted tiling scenario, and the determining of the size is repeated based on the adjusted tiling scenario. Responsive to the updated size not being less than the reference size, a preferred tiling scenario is identified based on the adjusted tiling scenario for tiling the video. Other embodiments are disclosed.

公开(公告)号：US10432524B2

公开(公告)日：2019-10-01

申请号：US15849200

申请日：2017-12-20

Applicant: AT&T Intellectual Property I, L.P. ,  Regents of the University of Minnesota

Inventor： Bo Han ,  Muhammad Bilal Anwer ,  Vijay Gopalakrishnan ,  Aman Shaikh ,  Joshua Reich ,  Yang Zhang ,  Zhi-Li Zhang

IPC: H04L12/741 ,  G06F9/455 ,  H04L12/721 ,  H04L12/815

Abstract: The concepts and technologies disclosed herein are directed to parallelism for virtual network functions (“VNFs”) in service function chains (“SFCs”). According to one aspect, a packet processing system can receive instructions to process, in parallel, at least a portion of a plurality of data packets associated with an SFC including a plurality of VNFs. The system can create a copy of at least the portion of the data packets. The system can send the copy of at least the portion of the data packets to at least two VNFs. The at least two VNFs can process, in parallel, the copy of at least the portion of the data packets. The system can receive, from the at least two VNFs, processed packets including the copy of at least the portion of the data packets and processed, in parallel, by the at least two VNFs. The system can combine the processed packets.

公开(公告)号：US10200753B1

公开(公告)日：2019-02-05

申请号：US15830631

申请日：2017-12-04

Applicant: AT&T Intellectual Property I, L.P.

Inventor： Shuai Hao ,  Bo Han ,  Moo-Ryong Ra

IPC: H04N21/442 ,  G06K9/00 ,  H04N21/462 ,  H04L29/06 ,  H04M1/725

Abstract: Aspects of the subject disclosure may include, for example, a method including detecting attention by a user to a presentation displayed at an audiovisual presentation device. A real-time image of the user is obtained and stored local to the audiovisual presentation device. The image is analyzed to determine a presence in the image of a facial feature of the user; the device determines, based on the presence of the facial feature, whether the user is attentive to the presentation. When the user is not attentive to the presentation, a procedure is initiated at the audiovisual presentation device to reduce resource consumption by the device; the procedure can include continuing the presentation at a video quality level lower than at the beginning of the presentation, reducing a brightness of the display, continuing the presentation with only the audio portion, and discontinuing the presentation. Other embodiments are disclosed.