Feature map construction method, visual positioning method and corresponding device

A feature map and construction method technology, applied in the field of visual positioning, can solve the problems of high cost, unfavorable promotion of automatic driving technology, etc., and achieve the effect of reducing the cost of use and peacekeeping

Active Publication Date: 2018-12-21
禾多科技(北京)有限公司
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In automatic driving technology, it is of great significance to obtain the pose of the vehicle in real time. However, in the existing vehicle positioning technology, the calculation of the pose of the vehicle usually relies on high-precision GPS sensors and high-precision laser radars. The cost of these devices is relatively high. Expensive, not conducive to the promotion of autonomous driving technology

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Feature map construction method, visual positioning method and corresponding device
  • Feature map construction method, visual positioning method and corresponding device
  • Feature map construction method, visual positioning method and corresponding device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0075] figure 2 A flow chart of the feature map construction method provided by the first embodiment of the present invention is shown. refer to figure 2 , the method includes:

[0076] Step S10: The processor 106 of the electronic device 100 obtains multiple frames of first images captured by the first camera installed on the first vehicle.

[0077] The feature map to be constructed by this method is usually aimed at a specific scene (the environment in which the vehicle is located), for example, the scene determined by the pre-planned vehicle driving route. Acquiring multiple frames of first images around the first vehicle. The electronic device 100 can be placed on the first vehicle, and the collected multiple frames of first images are input to the electronic device 100 for processing in real time; or the electronic device 100 can also be at the remote end, and the first vehicle communicates with the electronic device 100 through a wireless communication network conn...

no. 2 example

[0103] image 3 A flow chart of the visual positioning method according to the second embodiment of the present invention is shown. refer to image 3 , the method includes:

[0104] Step S20: The processor 106 of the electronic device 100 acquires a second image captured by a second camera installed on a second vehicle, and extracts a plurality of 2D feature points from the second image.

[0105] The visual positioning method in the second embodiment performs visual positioning on each frame of image captured by the second camera, and for the convenience of explanation, one frame of image is referred to as the second image. For the method of extracting 2D feature points from the second image, reference may be made to the relevant description in the first embodiment, and the description will not be repeated.

[0106] Step S21: The processor 106 of the electronic device 100 uses the second pose information collected by the low-precision integrated navigation device installed ...

no. 3 example

[0125] Figure 4 A functional block diagram of the feature map construction apparatus 200 provided by the third embodiment of the present invention is shown. refer to Figure 4 , the device consists of:

[0126] The first image collection module 210 is configured to obtain multiple frames of first images collected by the first camera mounted on the first vehicle;

[0127] The first image pose calculation module 220 is used to determine the pose of each frame of the first image using the first pose information collected by the high-precision integrated navigation device installed on the first vehicle;

[0128] The feature point tracking module 230 is configured to extract multiple 2D feature points from the first image of each frame, and construct multiple features based on the correspondence between each 2D feature point and the 2D feature points on the first image of other frames Trackers, wherein each feature tracker includes at least one 2D feature point with a correspon...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of vehicle positioning, and provides a feature map construction method, a visual positioning method and corresponding devices. The feature map constructionmethod comprises the following steps: obtaining a multi-frame first image acquired by a first camera; using a first pose information acquired by a high-precision combined navigation device to determine a pose of the first image of each frame; extracting a plurality of 2D feature points from the first image of each frame, and constructing a plurality of feature trackers by tracking a plurality of2D feature points; performing a triangulation calculation based on positions of the 2D feature points in each feature tracker on a corresponding first image, and a pose of the corresponding first image to obtain a 3D feature point corresponding to the feature tracker; and constructing a feature map based on a plurality of 3D feature points corresponding to the plurality of feature trackers. According to the feature map construction method, when the feature map is built, only the high-precision combined navigation device and the camera are used, so that the hardware cost in the vehicle positioning process can be effectively reduced.

Description

technical field [0001] The present invention relates to the field of visual positioning, in particular to a feature map construction method, a visual positioning method and a corresponding device. Background technique [0002] Self-driving car, also known as unmanned car, computer-driven car, or wheeled mobile robot, is a kind of intelligent car that realizes unmanned driving through a computer system. It has a history of several decades in the 20th century, and it has shown a trend close to practicality in the early 21st century. [0003] In automatic driving technology, it is of great significance to obtain the pose of the vehicle in real time. However, in the existing vehicle positioning technology, the calculation of the pose of the vehicle usually relies on high-precision GPS sensors and high-precision laser radars. The cost of these devices is relatively high. Expensive, not conducive to the promotion of autonomous driving technology. Contents of the invention [0...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G01C21/32G01C21/34
CPCG01C21/32G01C21/3415
Inventor 杜艳维
Owner 禾多科技(北京)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap