Title:
METHOD FOR TRAINING MODEL FOR POSITIONING, POSITIONING METHOD, ELECTRONIC DEVICE, AND MEDIUM
Document Type and Number:
WIPO Patent Application WO/2024/077449
Kind Code:
A1
Abstract:
The present application relates to the technical field of electronic devices, in particular to a method for training a model for positioning, a positioning method, an electronic device, and a medium. The method comprises: acquiring a plurality of pieces of visible light data under different ambient lights at a plurality of positions collected at the positions; and taking the visible light data, position information corresponding to the visible light data, and ambient light identifiers of the ambient lights corresponding to the visible light data as training data samples, inputting same into a first neural network model, and training the first neural network model to obtain a second neural network model. Therefore, according to the method for training the model for positioning provided by embodiments of the present application, the obtained second neural network model can be applied to positioning under multiple types of complex ambient light interference. Moreover, because the second neural network model is obtained by training by using visible light data under different ambient lights, the second neural network model can suppress the influence of ambient light and achieve high positioning accuracy.
More Like This:
Inventors:
ZHOU YAN (CN)
ZHUANG YUAN (CN)
YANG XIANSHENG (CN)
ZHUANG YUAN (CN)
YANG XIANSHENG (CN)
Application Number:
PCT/CN2022/124418
Publication Date:
April 18, 2024
Filing Date:
October 10, 2022
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06Q10/06
Attorney, Agent or Firm:
YINKE PATENT & TRADEMARK AGENT (SHANGHAI) LTD. (CN)
Download PDF: