Title:
VEHICLE POSITIONING METHOD BASED ON DEEP NEURAL NETWORK IMAGE RECOGNITION
Document Type and Number:
WIPO Patent Application WO/2020/083103
Kind Code:
A1
Abstract:
A vehicle positioning method based on deep neural network image recognition, and a training method for a deep neural network. The training method comprises: road marking graphic configuration (101), photographing device configuration (102), image sample collection (103), training sample making (104), deep neural network building (105), and deep neural network training (106). The image sample collection process is carried out in different periods under different illumination and weather conditions, so that the environmental adaptability of the deep neural network is improved. In addition, by taking sample images every certain angle in a traveling direction of a vehicle and the direction perpendicular to the traveling direction of the vehicle, a large amount of training sample data is obtained, the training precision for a deep neural network is improved, and thus the precision of vehicle positioning is improved.
Inventors:
FENG JIANGHUA (CN)
HU YUNQING (CN)
YUAN HAO (CN)
LIN JUN (CN)
LIU YUE (CN)
YOU JUN (CN)
XIONG QUNFANG (CN)
DING CHI (CN)
YUE WEI (CN)
HU YUNQING (CN)
YUAN HAO (CN)
LIN JUN (CN)
LIU YUE (CN)
YOU JUN (CN)
XIONG QUNFANG (CN)
DING CHI (CN)
YUE WEI (CN)
Application Number:
PCT/CN2019/111840
Publication Date:
April 30, 2020
Filing Date:
October 18, 2019
Export Citation:
Assignee:
CRRC ZHUZHOU INST CO LTD (CN)
International Classes:
G06K9/00
Foreign References:
| CN109446973A | 2019-03-08 | |||
| CN103925927A | 2014-07-16 | |||
| CN202350794U | 2012-07-25 | |||
| CN108009518A | 2018-05-08 | |||
| US20180211120A1 | 2018-07-26 |
Attorney, Agent or Firm:
SHANGHAI PATENT & TRADEMARK LAW OFFICE, LLC (CN)
Download PDF: