公开(公告)号：US11600070B2

公开(公告)日：2023-03-07

申请号：US17221947

申请日：2021-04-05

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

Inventor： Tarek Elgamal ,  Shu Shi ,  Varun Gupta ,  John Murray ,  Rittwik Jana

IPC: G06N3/08 ,  H04N7/18 ,  H04N19/87 ,  G06V20/40 ,  G06K9/62 ,  H04N5/232 ,  H04N19/114

Abstract: A system can obtain a labelled data set, including historic video data and labelled events. The system can divide the labelled data set into historic training/testing data sets. The system can determine, using the historic training data set, a plurality of different parameter configurations to be used by a video encoder to encode a video that includes a plurality of video frames. Each parameter configuration can include a group of pictures (“GOP”) size and a scenecut threshold. The system can calculate an accuracy of event detection (“ACC”) and a filtering rate (“FR”) for each parameter configuration. The system can calculate, for each parameter configuration of the plurality of different parameter configurations, a harmonic mean between the ACC and the FR. The system can then select a best parameter configuration of the plurality of different parameter configurations based upon the parameter configuration that has the highest harmonic mean.

公开(公告)号：US10970555B2

公开(公告)日：2021-04-06

申请号：US16552443

申请日：2019-08-27

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

Inventor： Tarek Elgamal ,  Shu Shi ,  Varun Gupta ,  John Murray ,  Rittwik Jana

IPC: G06K9/00 ,  G06N3/08 ,  G06K9/62 ,  H04N19/87 ,  H04N5/232 ,  H04N7/18 ,  H04N19/114

Abstract: A system can obtain a labelled data set, including historic video data and labelled events. The system can divide the labelled data set into historic training/testing data sets. The system can determine, using the historic training data set, a plurality of different parameter configurations to be used by a video encoder to encode a video that includes a plurality of video frames. Each parameter configuration can include a group of pictures (“GOP”) size and a scenecut threshold. The system can calculate an accuracy of event detection (“ACC”) and a filtering rate (“FR”) for each parameter configuration. The system can calculate, for each parameter configuration of the plurality of different parameter configurations, a harmonic mean between the ACC and the FR. The system can then select a best parameter configuration of the plurality of different parameter configurations based upon the parameter configuration that has the highest harmonic mean.

公开(公告)号：US20210224549A1

公开(公告)日：2021-07-22

申请号：US17221947

申请日：2021-04-05

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

Inventor： Tarek Elgamal ,  Shu Shi ,  Varun Gupta ,  John Murray ,  Rittwik Jana

IPC: G06K9/00 ,  G06N3/08 ,  G06K9/62 ,  H04N5/232 ,  H04N7/18 ,  H04N19/87 ,  H04N19/114

Abstract: A system can obtain a labelled data set, including historic video data and labelled events. The system can divide the labelled data set into historic training/testing data sets. The system can determine, using the historic training data set, a plurality of different parameter configurations to be used by a video encoder to encode a video that includes a plurality of video frames. Each parameter configuration can include a group of pictures (“GOP”) size and a scenecut threshold. The system can calculate an accuracy of event detection (“ACC”) and a filtering rate (“FR”) for each parameter configuration. The system can calculate, for each parameter configuration of the plurality of different parameter configurations, a harmonic mean between the ACC and the FR. The system can then select a best parameter configuration of the plurality of different parameter configurations based upon the parameter configuration that has the highest harmonic mean.

公开(公告)号：US20210064884A1

公开(公告)日：2021-03-04

申请号：US16552443

申请日：2019-08-27

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

Inventor： Tarek Elgamal ,  Shu Shi ,  Varun Gupta ,  John Murray ,  Rittwik Jana

IPC: G06K9/00 ,  G06N3/08 ,  G06K9/62 ,  H04N19/87 ,  H04N5/232 ,  H04N7/18

Abstract: A system can obtain a labelled data set, including historic video data and labelled events. The system can divide the labelled data set into a historic training/testing data sets. The system can determine, using the historic training data set, a plurality of different parameter configurations to be used by a video encoder to encode a video that includes a plurality of video frames. Each parameter configuration can include a group of pictures (“GOP”) size and a scenecut threshold. The system can calculate an accuracy of event detection (“ACC”) and a filtering rate (“FR”) for each parameter configuration. The system can calculate, for each parameter configuration of the plurality of different parameter configurations, a harmonic mean between the ACC and the FR. The system can then select a best parameter configuration of the plurality of different parameter configurations based upon the parameter configuration that has the highest harmonic mean.