Visual inertial odometer scale estimation method and device

An odometer and inertial technology, applied in the field of autonomous driving, can solve the problems of scale divergence, positioning accuracy does not meet the requirements of mapping, and achieve the effect of accurate accuracy and cheap calculation.

Active Publication Date: 2021-08-06
BEIJING MOMENTA TECH CO LTD
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the GPS signal is blocked or interfered, especially in the long tunnel scene, the system returns to the ordinary VIO system, and the scale divergence is obvious, resulting in positioning accuracy that does not meet the requirements of mapping

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
  • Visual inertial odometer scale estimation method and device
  • Visual inertial odometer scale estimation method and device
  • Visual inertial odometer scale estimation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] see figure 1 , figure 1 is a schematic flow chart of a visual-inertial odometry scale estimation method provided by an embodiment of the present invention. This method is typically applied to scenarios where GPS signals are interfered or affected during automatic driving, such as long tunnel scenarios. The method can be performed by a visual-inertial odometer estimating device, which can be realized by means of software and / or hardware, and generally can be integrated in a vehicle-mounted computer, a vehicle-mounted industrial personal computer (Industrial personalComputer, IPC), and other vehicle-mounted terminals. The embodiments of the invention are not limited. Such as figure 1 As shown, the method provided in this embodiment specifically includes:

[0086] 110. When it is recognized that there is an endpoint of a dashed line segment in the current perceptual image, extract the endpoint of the dashed line segment, and match the endpoint of the dashed line segmen...

Embodiment 2

[0106] see figure 2 , figure 2 is a schematic flow chart of a visual-inertial odometry scale estimation method provided by an embodiment of the present invention. This embodiment is optimized on the basis of the foregoing embodiments, and is mainly applied to a road scene where there is no endpoint of a dashed line segment on the road. Such as figure 2 As shown, the method includes:

[0107] 210. When it is recognized that there is no endpoint of the dotted line segment in the current perception image, determine the road surface area within the set range ahead of the current vehicle, and extract the target road surface point whose gradient value is greater than the set threshold from the road surface area.

[0108] Exemplarily, when extracting target road surface points, the road surface area can be divided into grids, and feature points whose gradient values ​​are greater than the set threshold can be extracted from each grid, so as to ensure that enough and distributed...

Embodiment 3

[0119] see image 3 , image 3 It is a structural block diagram of a visual-inertial odometry scale estimation device provided by an embodiment of the present invention. Such as image 3As shown, the device specifically includes: a target dashed line endpoint determination module 310, a coordinate determination module 320, a current altitude determination module 330, and a scale estimation module 340; wherein,

[0120] The target dashed line segment endpoint determining module 310 is configured to extract the dashed line segment endpoint when it is recognized that there is a dashed line segment endpoint in the current perception image, and match the dashed line segment endpoint with the historical perception image containing the dashed line segment endpoint , get the endpoint of the matching target dotted line segment;

[0121] The coordinate determination module 320 is configured to determine the current first coordinate and the historical first coordinate of the end point...

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 embodiment of the invention discloses a visual inertial odometer scale estimation method and device, and the method comprises the steps: extracting a dotted line segment endpoint when the existence of the dotted line segment endpoint in a current perception image is recognized, and carrying out the matching of the dotted line segment endpoint with a historical perception image containing the dotted line segment endpoint, obtaining matched target dotted line segment endpoints; determining a current first coordinate and a historical first coordinate, corresponding to the current perception image and the historical perception image, of the end point of the target dotted line segment in a world coordinate system; determining the current height of the camera to the ground according to the equality relationship between the current first coordinate and the historical first coordinate and the height increment of the camera when the current perception image and the historical perception image are shot; and according to the current height to the ground and the reference height of the camera to the ground, determining an estimation scale of a visual inertial odometer VIO. By adopting the technical scheme, when the GPS signal is interfered or influenced, the scale of the VIO can be accurately estimated.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a method and device for estimating the scale of a visual-inertial odometer. Background technique [0002] The VIO (visual-inertialodometry, visual-inertial odometer) positioning system based on the fusion of cameras and IMUs is currently a very popular positioning framework. The IMU (Inertial measurement unit, inertial measurement unit) ensures the accuracy of trajectory calculation in a short period of time, but the error varies with the The accumulation of time is very fast; the camera constrains its own pose and speed direction by observing and tracking feature points in the surrounding environment, and at the same time makes the divergence of the scale slower than relying on IMU calculation alone. The camera complements the IMU to form a good positioning system. [0003] However, when the movement of the carrier lacks incentives, especially for the vehicle-mounted ...

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): G06T7/33G06T7/73G06T7/55G01C22/00
CPCG06T7/33G06T7/55G06T7/73G01C22/00
Inventor 沈雪峰
Owner BEIJING MOMENTA TECH CO LTD
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