-
公开(公告)号:US11776276B1
公开(公告)日:2023-10-03
申请号:US18305951
申请日:2023-04-24
Applicant: Hayden AI Technologies, Inc.
Inventor: Wiktor Muron , Maciej Budys , Andrei Liaukovich , Marcin Grzesiak , Michael Gleeson-May , Shaocheng Wang , Vaibhav Ghadiok , Morgan Kohler
IPC: G06V20/54 , G06V20/58 , G06V10/82 , G06V10/764
CPC classification number: G06V20/54 , G06V10/764 , G06V10/82 , G06V20/58 , G06V2201/08
Abstract: Disclosed herein are methods and systems for automatically validating evidence of traffic violations. One instance of a method comprises receiving an evidence package comprising video frames showing a vehicle involved in a potential traffic violation. The video frames can be input into one or more deep learning models to obtain a plurality of classification results. The method can further comprise generating a score based in part on the classification results and evaluating the score against one or more thresholds to determine whether the evidence package is automatically approved, is automatically rejected, or requires further review.
-
公开(公告)号:US12223733B2
公开(公告)日:2025-02-11
申请号:US18365631
申请日:2023-08-04
Applicant: Hayden AI Technologies, Inc.
Inventor: Wiktor Muron , Maciej Budys , Andrei Liaukovich , Marcin Grzesiak , Michael Gleeson-May , Shaocheng Wang , Vaibhav Ghadiok , Morgan Kohler
IPC: G06V20/54 , G06V10/764 , G06V10/82 , G06V20/58
Abstract: Disclosed herein are methods and systems for automatically validating evidence of traffic violations. One instance of a method comprises receiving an evidence package comprising video frames showing a vehicle involved in a potential traffic violation. The video frames can be input into one or more deep learning models to obtain a plurality of classification results. The method can further comprise generating a score based in part on the classification results and evaluating the score against one or more thresholds to determine whether the evidence package is automatically approved, is automatically rejected, or requires further review.
-