公开(公告)号：US20220402505A1

公开(公告)日：2022-12-22

申请号：US17820633

申请日：2022-08-18

Applicant: Verizon Connect Development Limited

Inventor： Matteo SIMONCINI ,  Douglas COIMBRA DE ANDRADE ,  Samuele SALTI ,  Leonardo TACCARI ,  Fabio SCHOEN ,  Francesco SAMBO ,  Leonardo SARTI

IPC: B60W40/09 ,  G06F21/35 ,  G07C5/00 ,  G07C5/08 ,  G08G1/00 ,  G06V20/56

Abstract: A maneuver classification platform may obtain video data and telematic data that are associated with a driving event involving a vehicle. The maneuver classification platform may analyze the video data to identify a path of the vehicle along a roadway during the driving event, and based on markings of a plurality of roadways. The maneuver classification platform may analyze the video data to determine a type of a vehicle maneuver performed by the vehicle during the driving event. The maneuver classification platform may determine a maneuver score of the driving event based on the type of the vehicle maneuver, the path of the vehicle, and the telematic data. The maneuver classification platform may send a message associated with the maneuver score and a vehicle identifier of the vehicle to a client device to permit the client device to use the maneuver score.

公开(公告)号：US20220084395A1

公开(公告)日：2022-03-17

申请号：US17456405

申请日：2021-11-24

Applicant: VERIZON CONNECT DEVELOPMENT LIMITED

Inventor： Samuele SALTI ,  Francesco SAMBO ,  Leonardo TACCARI ,  Luca BRAVI ,  Matteo SIMONCINI ,  Alessandro LORI

IPC: G08G1/015 ,  G01S19/42 ,  G01S19/52 ,  G07C5/00 ,  G06K9/62

Abstract: A method and system for classifying a vehicle based on low frequency GPS tracks. The method and system comprise retrieving a low frequency GPS track having a sampling interval of at least 20 seconds; deriving additional data from the low frequency GPS track, the additional data including interval speed and instantaneous acceleration of the vehicle; extracting a plurality of data sets from the low frequency GPS track and the additional data; generating a plurality of features from the extracted data sets; and providing the plurality of generated features to a classifier that classifies the vehicle into a predetermined class.

公开(公告)号：US20210354704A1

公开(公告)日：2021-11-18

申请号：US16947918

申请日：2020-08-24

Applicant: Verizon Connect Development Limited

Inventor： Matteo SIMONCINI ,  Douglas COIMBRA DE ANDRADE ,  Samuele SALTI ,  Leonardo TACCARI ,  Fabio SCHOEN ,  Francesco SAMBO ,  Leonardo SARTI

IPC: B60W40/09 ,  G07C5/08 ,  G07C5/00 ,  G06K9/00 ,  G06F21/35 ,  G08G1/00

Abstract: A maneuver classification platform may obtain video data and telematic data that are associated with a driving event involving a vehicle. The maneuver classification platform may analyze the video data to identify a path of the vehicle along a roadway during the driving event, and based on markings of a plurality of roadways. The maneuver classification platform may analyze the video data to determine a type of a vehicle maneuver performed by the vehicle during the driving event. The maneuver classification platform may determine a maneuver score of the driving event based on the type of the vehicle maneuver, the path of the vehicle, and the telematic data. The maneuver classification platform may send a message associated with the maneuver score and a vehicle identifier of the vehicle to a client device to permit the client device to use the maneuver score.

公开(公告)号：US20220327833A1

公开(公告)日：2022-10-13

申请号：US17810003

申请日：2022-06-30

Applicant: Verizon Connect Development Limited

Inventor： Francesco SAMBO ,  Leonardo TACCARI ,  Marco BOSCHI ,  Luca DE LUIGI ,  Samuele SALTI

IPC: G06V20/40 ,  G06T7/20 ,  G08G1/00 ,  G07C5/00 ,  G06T17/20

Abstract: A device may receive, from a first vehicle, video data for video captured of a location associated with an accident for a second vehicle, and may process the video data, with a first model, to generate a sparse point cloud of the location associated with the accident. The device may process the video data, with a second model, to generate depth maps for frames of the video data, and may utilize the depth maps with the sparse point cloud to generate a dense point cloud. The device may process the video data, with a third model, to generate a dense semantic point cloud, and may process the dense semantic point cloud, with a fourth model, to determine a dense semantic overhead view of the location associated with the accident. The device may perform actions based on the dense semantic overhead view.