公开(公告)号：US20220120582A1

公开(公告)日：2022-04-21

申请号：US17562432

申请日：2021-12-27

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Xinxin PEI ,  Wei YU

IPC: G01C21/36 ,  G01C21/34 ,  G01C21/30

Abstract: The present disclosure provides a route processing method and apparatus. The specific implementation includes: acquiring a vehicle driving route according to a standard definition map, where the vehicle driving route comprises multiple standard definition map road sections of the standard definition map; determining at least one first road section from the multiple standard definition map road sections according to a road section mapping relationship between the standard definition map and a high definition map, where each first road section has a unique corresponding target road section in the high definition map; determining the target road section corresponding to each first road section in the high definition map according to the road section mapping relationship; and determining a target driving route corresponding to the vehicle driving route in the high definition map according to the target road section corresponding to each first road section and the high definition map.

公开(公告)号：US20220327803A1

公开(公告)日：2022-10-13

申请号：US17809210

申请日：2022-06-27

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Wei YU ,  Kun WANG

IPC: G06V10/75 ,  G06V10/40 ,  G06V10/82 ,  G06V10/774 ,  G06V10/80 ,  G06V10/776 ,  G06V10/74 ,  G06V10/22

Abstract: A method of recognizing an object, an electronic device and storage medium are provided, which relate to a field of data processing, in particular to a field of object recognition. The method includes: acquiring a position information and an image data of an object to be detected; performing a feature extraction on the position information and the image data of the object to be detected to obtain a first target concatenating feature; inputting the first target concatenating feature into a pre-trained deep learning model to obtain a second target concatenating feature; determining a second sample concatenating feature matched with the second target concatenating feature by matching the second target concatenating feature with each second sample concatenating feature obtained by processing a first sample concatenating feature of a sample object; and determining the object to be detected as the sample object corresponding to the second sample concatenating feature.