Unlock instant, AI-driven research and patent intelligence for your innovation.

Vehicle visual positioning method, system and device and readable storage medium

A visual positioning and vehicle technology, applied in the field of image processing, can solve problems such as drift errors, achieve the effects of reducing development costs, simplifying the positioning system, and reducing complexity

Pending Publication Date: 2022-04-08
CHANGAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a vehicle visual positioning method, system, equipment and readable storage medium, to overcome the drift error problem caused by the existing visual positioning method

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
  • Vehicle visual positioning method, system and device and readable storage medium
  • Vehicle visual positioning method, system and device and readable storage medium
  • Vehicle visual positioning method, system and device and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0102] Comply with the above technical solutions, such as Figure 1 to Figure 9 As shown, this embodiment provides a vehicle visual positioning device, including a high-definition binocular camera with a resolution of 1600*1200 installed at the interior rearview mirror of the vehicle, and the main optical axis of the camera is parallel to the vehicle base and Before, use the RJ-45 network data line to connect the camera with the LAN interface to the Gigabit network switch, transmit the data to the server for processing and obtain the positioning result, use the vehicle power supply combined with the inverter as the power supply for the equipment, and obtain The high-precision positioning information is used for later decision-making and state control of intelligent vehicles, the Basler aca1600-60gc high-definition camera ensures the amount of image information, the Cisco WS-C3560X-24T-L Gigabit network switch ensures data transmission speed, and the AMAX PSC-6S server To ensur...

Embodiment 2

[0192] Example 2: Algorithm Verification in a Real Environment

[0193] In order to illustrate the high accuracy of the visual positioning method in the present invention, experimental verification was carried out in a real environment, compared with a high-precision DGPS, the model is NovAtel OEM6TM GNSS, and its dual antennas are respectively attached to the front and rear of the central axis of the vehicle roof . The original video image collected by the binocular camera is transmitted to the gigabit network switch through the network cable, and then transmitted from the gigabit network switch to the server for data processing; while the DGPS data is directly transmitted to the server through the serial port. Figure 9 The experimental verification results are shown, among which, VISO2 means the positioning result obtained by using the LIBVISO2 visual odometry method, and DGPS means the high-precision vehicle trajectory obtained by using differential GPS.

[0194] in such ...

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 discloses a vehicle visual positioning method, system and device and a readable storage medium, and the method comprises the steps: carrying out the parameterization of a rotation matrix in a vehicle motion process into an angle variable quantity, carrying out the parameterization of a translation vector in the vehicle motion process into a translation component, representing the translation component through a graph theory concept, and carrying out the feature detection of a robust feature point AKAZE based on a feature detection algorithm. The accuracy of feature point extraction and feature point association is ensured by combining a zero-mean normalized cross-correlation and multi-strategy feature point matching algorithm, noise points and wrong matching points are removed by an outer point removal algorithm of an improved RANSAC algorithm, and the accuracy of motion calculation is ensured. Vehicle motion information is solved through a nonlinear weighted least square method, a motion result is further optimized based on a Sigma point filtering processing technology, the positioning precision is high, the improved RANSAC algorithm based on initial value estimation reduces the complexity of exterior point removal, the real-time performance of the algorithm is ensured, the number of feature points is reduced, the complexity of the algorithm is reduced, and the positioning accuracy is improved. And the real-time performance of the whole algorithm is ensured.

Description

technical field [0001] The invention belongs to the field of image processing and relates to a visual positioning method, in particular to a vehicle visual positioning method, system, equipment and a readable storage medium. Background technique [0002] The existing vehicle positioning methods have many technical defects. For example, the traditional odometer has a large positioning error on wet and slippery ground, and GNSS will drift greatly or fail to locate directly under the condition of lack of satellites. However, based on incremental positioning The current IMU cannot overcome the defect of cumulative error. LiDAR has high positioning accuracy, but its real-time performance is poor, and the equipment is expensive. The fusion positioning method using multiple sensors has received high attention and research in recent years. The technical implementation is more complicated and the cost is higher. [0003] With the development of image processing technology, high-prec...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06V20/62G06V10/40G06K9/62G06V10/75
Inventor 闵海根吴霞方煜坤王武祺邢凡盛李尧雷小平夏森刘占文龚思远王润民王振蒋渊德
Owner CHANGAN UNIV