Vehicle positioning method based on image detection, and vehicle-mounted terminal

Abstract

The embodiment of the invention discloses a vehicle positioning method based on image detection, and a vehicle-mounted terminal. The method comprises the following steps: determining an initial positioning pose corresponding to a road image according to data collected by a motion detection device; determining each first map point corresponding to the road image from each map point of a preset map according to the initial positioning pose; detecting an object contour area of the road image according to a preset semantic contour detection algorithm; and according to the initial positioning pose, determining a mapping difference between the second map point and the detected contour point of the object contour area, and according to the mapping difference, determining an optimized positioning pose of the vehicle. The second map point is a map point on the object contour in each first map point, and each map point of the preset map is obtained by performing three-dimensional reconstruction on points in each object contour area in the sample road image in advance. By applying the scheme provided by the embodiment of the invention, the effectiveness of positioning the vehicle based on vision can be improved.

Description

technical field [0001] The present invention relates to the technical field of intelligent driving, in particular, to an image detection-based vehicle positioning method and a vehicle-mounted terminal. Background technique [0002] In the field of intelligent driving technology, vehicle positioning is an important part of intelligent driving. Usually, when the vehicle is driving, the vehicle pose can be determined according to the satellite positioning system. However, when the vehicle travels to a scene with weak or no satellite signal, in order to accurately determine the positioning pose of the vehicle, visual positioning can be used for positioning. [0003] Visual positioning is usually based on the matching between the semantic information of the road image collected by the camera device and the semantic information in the high-precision map. The semantic information in the high-precision map is modeled based on common landmarks on the road. Markers generally includ...

AI Technical Summary

Problems solved by technology

However, when there are few landmarks or even no landmarks in the scene, it is difficult for the high-precision map to give enough effective information for visual positioning; or, when the landmarks cannot completely match the high-precision map due to occlusion or aging, the visual positioning may not be possible

All of the above lead to less effective visual localization

Images