公开(公告)号：US12243328B2

公开(公告)日：2025-03-04

申请号：US17820317

申请日：2022-08-17

Applicant: GM Global Technology Operations LLC

Inventor： Jiejun Xu ,  Kenji Yamada ,  Michael J. Daily ,  Alireza Esna Ashari Esfahani ,  Hyukseong Kwon ,  Darren Michael Chan ,  Alan Perry ,  Joshua Lampkins

IPC: G06V20/58 ,  G06N3/045 ,  G06V10/82 ,  G06V20/62 ,  G06V30/262

Abstract: A road sign interpretation system includes a front-facing camera mounted on or in a vehicle collecting image data of multiple road signs. A first convolutional neural network (CNN) receives the image data from the front-facing camera and yields a set of sign predictions including one or more sign text instances. A second CNN defining a text extractor receives the image data from the front-facing camera and extracts text candidates including the multiple sign text instances. Sign and sign data localization is provided in the second CNN to compute a text order from the multiple sign text instances. A sign text synthesizer module receives individual sign text instances from the first CNN and individual ones of the sign text instances in digitized forms from an optical character recognizer (OCR). A semantic encoding and interpretation module receives the sign text instances and identifies semantics of the multiple road signs.

公开(公告)号：US20240062555A1

公开(公告)日：2024-02-22

申请号：US17820317

申请日：2022-08-17

Applicant: GM Global Technology Operations LLC

Inventor： Jiejun Xu ,  Kenji Yamada ,  Michael J. Daily ,  Alireza Esna Ashari Esfahani ,  Hyukseong Kwon ,  Darren Michael Chan ,  Alan Perry ,  Joshua Lampkins

IPC: G06V20/58 ,  G06V20/62 ,  G06V10/82 ,  G06V30/262 ,  G06N3/04

CPC classification number: G06V20/582 ,  G06V20/63 ,  G06V10/82 ,  G06V30/274 ,  G06N3/0454

Abstract: A road sign interpretation system includes a front-facing camera mounted on or in a vehicle collecting image data of multiple road signs. A first convolutional neural network (CNN) receives the image data from the front-facing camera and yields a set of sign predictions including one or more sign text instances. A second CNN defining a text extractor receives the image data from the front-facing camera and extracts text candidates including the multiple sign text instances. Sign and sign data localization is provided in the second CNN to compute a text order from the multiple sign text instances. A sign text synthesizer module receives individual sign text instances from the first CNN and individual ones of the sign text instances in digitized forms from an optical character recognizer (OCR). A semantic encoding and interpretation module receives the sign text instances and identifies semantics of the multiple road signs.