公开(公告)号：US11328505B2

公开(公告)日：2022-05-10

申请号：US16793829

申请日：2020-02-18

Applicant: Verizon Connect Development Limited

Inventor： Leonardo Taccari ,  Luca Kubin ,  Tommaso Bianconcini ,  Andrea Benericetti ,  Leonardo Sarti ,  Tommaso Innocenti

IPC: G06K9/00 ,  G06V20/10 ,  G06N3/04 ,  B64C39/02 ,  G08G1/16

Abstract: A device may receive sensor data and video data associated with a vehicle, and may process the sensor data, with a rule-based detector model, to determine whether a probability of a vehicle accident satisfies a first threshold. The device may preprocess acceleration data of the sensor data to generate calibrated acceleration data, and may process the calibrated acceleration data, with an anomaly detector model, to determine whether the calibrated acceleration data includes anomalies. The device may filter the sensor data to generate filtered sensor data, and may process the filtered sensor data and anomaly data, with a decision model, to determine whether the probability of the vehicle accident satisfies a second threshold. The device may process the filtered sensor data, the anomaly data, and the video data, with a machine learning model, to determine whether the vehicle accident has occurred, and may perform one or more actions.

公开(公告)号：US11756431B2

公开(公告)日：2023-09-12

申请号：US17659928

申请日：2022-04-20

Applicant: Verizon Connect Development Limited

Inventor： Leonardo Taccari ,  Luca Kubin ,  Tommaso Bianconcini ,  Andrea Benericetti ,  Leonardo Sarti ,  Tommaso Innocenti

IPC: G06V20/10 ,  G08G1/00 ,  G06N3/04 ,  B64C39/02 ,  G08G1/16 ,  G06V10/771 ,  G06V10/80 ,  G06V10/98 ,  G06V20/56 ,  B64U101/30

CPC classification number: G08G1/205 ,  B64C39/024 ,  G06N3/04 ,  G06V10/771 ,  G06V10/806 ,  G06V10/98 ,  G06V20/10 ,  G06V20/56 ,  G08G1/164 ,  B64U2101/30

Abstract: A device may receive sensor data and video data associated with a vehicle, and may process the sensor data, with a rule-based detector model, to determine whether a probability of a vehicle accident satisfies a first threshold. The device may preprocess acceleration data of the sensor data to generate calibrated acceleration data, and may process the calibrated acceleration data, with an anomaly detector model, to determine whether the calibrated acceleration data includes anomalies. The device may filter the sensor data to generate filtered sensor data, and may process the filtered sensor data and anomaly data, with a decision model, to determine whether the probability of the vehicle accident satisfies a second threshold. The device may process the filtered sensor data, the anomaly data, and the video data, with a machine learning model, to determine whether the vehicle accident has occurred, and may perform one or more actions.