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

A vehicle slam mapping method and system

A technology for vehicles and maps, which is applied in the field of SLAM mapping methods and systems for vehicles, and can solve the problems of lack of environmental information on maps and low success rate of mapping, etc.

Active Publication Date: 2021-02-19
GUANGZHOU XIAOPENG MOTORS TECH CO LTD
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the timing of successful initialization is late, the vehicle needs to drive a long distance to start mapping, which may lead to a low success rate of mapping, and may also easily lead to the lack of some environmental information in the constructed map

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
  • A vehicle slam mapping method and system
  • A vehicle slam mapping method and system
  • A vehicle slam mapping method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] see figure 1 , figure 1 It is a schematic flowchart of a vehicle SLAM mapping method disclosed in an embodiment of the present invention. in, figure 1 The described vehicle SLAM mapping method is applicable to vehicle-mounted electronic equipment such as a vehicle-mounted computer and an electronic control unit (Electronic Control Unit, ECU), and is not limited in the embodiments of the present invention. Such as figure 1 As shown, the SLAM mapping method of the vehicle may include the following steps:

[0074] 101. The on-vehicle electronic device acquires two initial frames respectively captured by any two camera modules of the vehicle when the vehicle is stationary.

[0075] In the embodiment of the present invention, the viewing ranges of the two camera modules overlap at least partially. As an optional implementation manner, the above two camera modules may be any two camera modules in a multi-eye camera system. The multi-eye camera system can include three o...

Embodiment 2

[0093] see figure 2 , figure 2 It is a schematic flowchart of another vehicle SLAM mapping method disclosed in the embodiment of the present invention. Such as figure 2 As shown, the SLAM mapping method of the vehicle may include the following steps:

[0094] 201. The on-vehicle electronic device acquires two initial frames respectively captured by any two camera modules of the vehicle when the vehicle is stationary.

[0095] In the embodiment of the present invention, the above-mentioned two camera modules may be any two camera modules in a multi-eye camera system, and the focal lengths and field angles of the two camera modules may be the same or different. However, due to the large number of camera modules in the multi-camera system, in order to reduce the amount of image data processing and speed up the processing time, a camera module with a fixed focal length is generally selected. Further, in order to expand the observation distance that can be covered, different...

Embodiment 3

[0114] see image 3 , image 3 It is a schematic flowchart of another vehicle SLAM mapping method disclosed in the embodiment of the present invention. Such as image 3 As shown, the SLAM mapping method of the vehicle may include the following steps:

[0115] Steps 301 to 304 are the same as steps 101 to 104, wherein the specific implementation of step 304 can be as shown in steps 204 to 206, and the following content will not be repeated.

[0116] 305. During relocation, the vehicle-mounted electronic device acquires multiple frames of target images captured by the target camera module and the aforementioned global SLAM map.

[0117] In the embodiment of the present invention, the global SLAM map is a digital description of the real environment. After the global SLAM map is constructed, the vehicle electronic device can reuse the global SLAM map. Similar to the way humans use maps for positioning, on-board electronic devices can locate the position of the vehicle in the g...

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

A SLAM mapping method and system for a vehicle, the method comprising: acquiring two initial frames respectively captured by any two camera modules of the vehicle; wherein, the focal lengths and field angles of the two camera modules can be the same, or Can be different; according to the internal parameters and external parameters of the two camera modules and the parallax of the matching feature points in the two initial frames, determine the three-dimensional space positions of the matching feature points to obtain the corresponding map points, to construct an initial SLAM map to complete the initialization; after the initialization is successful, obtain the image captured by any one of the target camera modules in the two camera modules; based on the initial SLAM map, combined with the target camera module The images captured by the group are used for monocular vision SLAM construction, so that the initialization can be completed through the binocular camera. After the initialization is successful, the monocular camera is used to construct the map, which reduces the computing load of the system and improves the success rate of map construction. .

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a vehicle SLAM mapping method and system. Background technique [0002] In the field of autonomous driving, Simultaneous Localization and Mapping (SLAM) refers to the use of a single visual sensor (such as a camera) by an autonomous vehicle to create a map that is consistent with the real environment, and at the same time determine itself in the map. s position. [0003] However, traditional monocular vision SLAM can only be initialized through a dynamic method, that is, it needs to use images captured during camera movement to be successfully initialized. Therefore, when drawing a map, it is necessary to drive the vehicle a certain distance first, and then start to build the map after completing the initialization of the monocular vision SLAM. If the initialization succeeds later, the vehicle needs to drive a longer distance to start mapping, which may lead t...

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 Patents(China)
IPC IPC(8): G06T17/05G06T7/70
CPCG06T7/579G06T7/73G06T2207/30244G06T2207/30252
Inventor 周建李良王磊刚刘中元肖志光
Owner GUANGZHOU XIAOPENG MOTORS TECH CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com