Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Drivable region identification method based on positioning and image and map matching

A driving area and map matching technology, which is applied in transportation and packaging, two-dimensional position/channel control, vehicle position/route/height control, etc., can solve problems such as difficult implementation, achieve simple structure, strong versatility, avoid Non-real-time effects

Active Publication Date: 2017-09-22
JIANGSU UNIV
View PDF10 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since automatic driving in all working conditions cannot be realized immediately, automatic driving in local areas is not difficult to realize due to the simple environment structure

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
  • Drivable region identification method based on positioning and image and map matching
  • Drivable region identification method based on positioning and image and map matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings and specific examples. It should be pointed out that the following is only an optimized technical solution and design principle for illustration, but the protection scope of the present invention is not limited thereto.

[0020] The present invention proposes a drivable area recognition method based on location-based image and map matching adapted to underground parking lot ramps. The positioning coordinates of the current vehicle in the ramp are obtained by the autonomous vehicle internal positioning system. Based on this positioning coordinates, the The map data ahead of the current position is extracted from the high-precision map of the ramp, and at this time the recognition system extracts the image from the camera in the middle of the front bumper of the autonomous vehicle, and points match the map data of the current position with the camera image to obtain the front...

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 drivable region identification method based on positioning and image and map matching. The drivable region identification method comprises the steps of: 1) acquiring a position of an autonomous vehicle in a ramp at a moment by means of a positioning system in the vehicle when the autonomous vehicle enters the ramp of an underground parking lot for unmanned driving; 2), extracting information of the ramp ahead of a current position by means of a drivable region identification system according to the position acquired by means of the positioning system, and extracting an image in a current vehicle camera by means of the drivable region identification system; 3) and performing point matching on an image extracted from a high-precision map and the map obtained by the camera, and inputting a result of image matching integration into the drivable region identification system, so as to identify walls, separation facilities and other vehicles existing in the front region. The drivable region identification method solves the problem of driving region identification in the ramp for regional autonomous driving of the underground parking lot in future, has high universality, and has high identification precision and real-time performance.

Description

technical field [0001] The invention relates to the field of automatic driving, in particular to a drivable area recognition method based on positioning image and map matching. Background technique [0002] More and more car companies and Internet companies are vigorously deploying autonomous driving technology. At present, various companies also have some rudimentary autonomous driving vehicles that have been reported. [0003] However, due to the complexity and unpredictability of the working conditions and the limitations of current technology in order to realize the automatic driving under all working conditions, it is difficult to make a major breakthrough in the real automatic driving under all working conditions in the near future. . Like Google, even though self-driving vehicles have been tested on actual roads for a long distance, they dare not rush to launch fully automatic driving. [0004] At present, it is difficult to implement autonomous driving products, wh...

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): G05D1/02
CPCG05D1/0214G05D1/0251G05D1/0257G05D1/0276
Inventor 江浩斌张旭培马世典
Owner JIANGSU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products