Title:
MACHINE LEARNING-BASED ASSISTED DRIVING METHOD AND APPARATUS, AND COMPUTER-READABLE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2023/173699
Kind Code:
A1
Abstract:
The present invention relates to a machine learning-based assisted driving method and apparatus, and a computer-readable medium. The method comprises: acquiring training data, the training data comprising a plurality of images of a target road section under different weather conditions, and each image having a certain visibility; constructing a machine learning model and inputting the training data into the machine learning model, the output result of the machine learning model comprising the visibility of each image; acquiring a first image of the target road section, and inputting the first image into the trained machine learning model, a first output result of the trained machine learning model comprising the current visibility of the first image; performing defogging processing on the first image according to the current visibility, and obtaining a second image; and providing visual information on a vehicle-mounted display device according to the second image.
More Like This:
Inventors:
HUO NING (CN)
Application Number:
PCT/CN2022/116658
Publication Date:
September 21, 2023
Filing Date:
September 02, 2022
Export Citation:
Assignee:
HOZON NEW ENERGY AUTOMOBILE CO LTD (CN)
International Classes:
G06N20/00; G06T5/00; G06V20/56; G06V20/58
Domestic Patent References:
WO2021229458A1 | 2021-11-18 |
Foreign References:
CN114626472A | 2022-06-14 | |||
CN111259957A | 2020-06-09 | |||
CN114037630A | 2022-02-11 | |||
CN109829386A | 2019-05-31 | |||
CN110097519A | 2019-08-06 | |||
CN109117691A | 2019-01-01 | |||
US20090161914A1 | 2009-06-25 |
Attorney, Agent or Firm:
SHANGHAI PATENT & TRADEMARK LAW OFFICE, LLC (CN)
Download PDF: