Device, system and method for drawing landmark map based on binocular vision

Abstract

The embodiment of the invention provides a device, system and method for drawing a landmark map based on binocular vision. The device comprises a first lens, a first prism, a second prism, an image sensor, an image processing module and a GNSS differential positioning module. The first lens and the first prism are symmetrically arranged along the central axis of the second prism, wherein the first lens and the first prism located on one side of the second prism sequentially form a left light path, and the first lens and the first prism located on the other side of the second prism sequentially form a right light path. The light along the left light path and the light along the right light path are reflected to the image sensor through the second prism. The image sensor is used for obtaining an image collected by a binocular lens and transmitting the image to the image processing module. The image processing module is used for analyzing and processing image data. The GNSS differential positioning module is used for obtaining the coordinate of the original point of the lens coordinate system in the world coordinate system through GNSS differential positioning. The requirement on a processor is reduced, the precision is high, and the cost is low.

Description

technical field [0001] The present invention relates to the technical field of map surveying and mapping, in particular to a device, system and method for drawing landmark maps based on binocular vision. Background technique [0002] Binocular Stereo Vision (Binocular Stereo Vision): It is an important form of machine vision. It is based on the principle of parallax and uses imaging equipment to obtain two images of the measured object from different positions. By calculating the position deviation between the corresponding points of the image , to obtain the three-dimensional geometric information of the object. [0003] High-precision landmark map: High-precision landmark map stores a large amount of driving assistance information as structured data. One type is road data, such as lane information such as the position, type, width, slope, and curvature of lane lines. The second category is fixed object information around the lane, such as traffic signs, traffic lights and...

AI Technical Summary

Problems solved by technology

[0004] At present, the mainstream landmark map drawing scheme: use a variety of sensors, such as GPS, inertial measurement unit, lidar and camera, collect a large amount of data through a variety of sensors, and finally draw a high-precision map, which is often complicated and expensive

At the same time, its recognition ability is often difficult to further improve

Images