Vehicle positioning method

Abstract

The invention discloses a vehicle positioning method which comprises the following steps: collecting a plurality of training samples as a training set N, and taking a picture with a training area driving environment marker shot by a vehicle camera and a high-precision map of a training area where a vehicle is located when the picture is shot as a sample n in the training set, wherein n belongs toN; adopting a deep learning method, the training set is used for training a model, and a trained model is obtained; when the vehicle enters the prediction area; shooting the driving environment markerin the prediction area to obtain a picture shot in the prediction area, inputting the picture shot in the prediction area and the processed high-precision map which is cached in advance and comprisesthe prediction area into the trained model, and determining the high-precision map of the prediction area where the current vehicle is located; And the current vehicle position coordinate is determined. By the adoption of the method and device, vehicle positioning in the environment where the positioning process does not completely depend on satellite signals and cannot receive the signals can beachieved.

Description

technical field [0001] The invention relates to the technical field of positioning, in particular to a vehicle positioning method. Background technique [0002] Vehicle positioning technology is an important technology in the field of intelligent autonomous driving, and the demand for high-precision and high-reliability vehicle positioning is increasing day by day. At present, the most widely used and most mature positioning technology is the Global Positioning System (GPS, Global Positioning System), which has the characteristics of high cost performance, simple deployment, and global coverage. On this basis, there are many improved enhancement technologies, such as real-time dynamic differential positioning, visual odometer, inertial navigation positioning, dead reckoning positioning, etc., which improve the positioning accuracy and positioning update frequency of the satellite positioning system to a certain extent. Today's GPS systems can provide very accurate position ...

AI Technical Summary

Problems solved by technology

[0005] In addition, there is a more common limiting factor in map-based vehicle location technology

During the driving process of the vehicle, due to factors such as camera shake and insufficient lighting, the collected images will be blurred to a certain extent, which will have some impact on the feature matching process, thereby affecting the positioning accuracy

Images