公开(公告)号：US11954916B2

公开(公告)日：2024-04-09

申请号：US17665895

申请日：2022-02-07

Applicant: GM Global Technology Operations LLC

Inventor： Wei Tong ,  Siddhartha Gupta ,  Jacob Alan Bond ,  Zhuoning Yuan

IPC: G06V20/00 ,  B60W40/04 ,  B60W60/00 ,  G06V10/40 ,  G06V10/74 ,  G06V10/764 ,  G06V10/82 ,  G06V20/58

CPC classification number: G06V20/58 ,  B60W40/04 ,  B60W60/001 ,  G06V10/40 ,  G06V10/761 ,  G06V10/764 ,  G06V10/82 ,  B60W2420/403 ,  B60W2554/4026 ,  B60W2554/4029

Abstract: An automated driving system includes an object detection system. A neural network image encoder generates image embeddings associated with an image including an object. A neural network text encoder generates concept embeddings associated with each of a plurality of concepts. Each of the plurality of concepts is associated with one of at least two object classes. A confidence score module generates a confidence score for each of the plurality of concepts based on the image embeddings and the concept embeddings associated with the concept. An object class prediction module generates a predicted object class of the object based on an association between a set of concepts of the plurality of concepts having at least two of the highest values of the generated confidence scores and the one of the at least two object classes associated with a majority of the set of concepts.

公开(公告)号：US20230252795A1

公开(公告)日：2023-08-10

申请号：US17665895

申请日：2022-02-07

Applicant: GM Global Technology Operations LLC

Inventor： Wei Tong ,  Siddhartha Gupta ,  Jacob Alan Bond ,  Zhuoning Yuan

IPC: G06V20/58 ,  G06V10/82 ,  G06V10/764 ,  G06V10/40 ,  G06V10/74 ,  B60W60/00 ,  B60W40/04

CPC classification number: G06V20/58 ,  G06V10/82 ,  G06V10/764 ,  G06V10/40 ,  G06V10/761 ,  B60W60/001 ,  B60W40/04 ,  B60W2554/4026 ,  B60W2554/4029 ,  B60W2420/42

Abstract: An automated driving system includes an object detection system. A neural network image encoder generates image embeddings associated with an image including an object. A neural network text encoder generates concept embeddings associated with each of a plurality of concepts. Each of the plurality of concepts is associated with one of at least two object classes. A confidence score module generates a confidence score for each of the plurality of concepts based on the image embeddings and the concept embeddings associated with the concept. An object class prediction module generates a predicted object class of the object based on an association between a set of concepts of the plurality of concepts having at least two of the highest values of the generated confidence scores and the one of the at least two object classes associated with a majority of the set of concepts.