Underground parking lot scene identification method based on upward view angle image features

An underground parking lot and scene recognition technology, which is applied in the field of underground parking scene recognition, can solve problems such as inability to apply, achieve the effect of preventing image matching problems and improving efficiency and accuracy

Pending Publication Date: 2022-04-15
HUBEI UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above two methods do not use the upward viewing angle to realize scene recognition, and are based on GPS to realize scene recognition, which cannot be applied to the underground parking lot environment without GPS

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
  • Underground parking lot scene identification method based on upward view angle image features
  • Underground parking lot scene identification method based on upward view angle image features
  • Underground parking lot scene identification method based on upward view angle image features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0039] like figure 1 As shown, a multi-scale scene recognition method of an underground parking lot based on the local feature matching of the upward-looking perspective image, the method of the present invention is characterized in that the node-type map is constructed, and the multi-scale scene recognition method based on the LDB image feature matching of the upward-looking perspective is as follows: figure 2 shown, including the following steps:

[0040] Step 1: Deploy the first wireless transmitter module and the second wireless transmitter module at th...

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 an underground parking lot scene identification method based on upward view angle image features. The method aims at an indoor environment of an underground parking lot without GPS signals, takes an upward view angle as an object, and constructs an atlas set containing image local features of a downward view angle and a multi-scale scene based on the atlas set. The method comprises the steps of extraction and matching of local features of an upward view angle image, construction of a map set and multi-scale positioning of the underground parking lot. Compared with the traditional positioning method for extracting the local features of the front-view image, the method provided by the invention can effectively overcome the problem of mismatching of the image features caused by the free shooting angle of the user as the local features of the image at the upward view angle are extracted as the positioning features. Besides, the map node closest to the node to be positioned can be accurately and efficiently found by matching the positioning features of different scales, so that scene recognition is realized, and a navigation basis is provided for vehicle searching and positioning of the underground parking lot.

Description

technical field [0001] The invention relates to the field of vehicle positioning, in particular to an underground parking lot scene recognition method based on image features of an upward viewing angle. Background technique [0002] Scene recognition is to locate the map node closest to the node to be located, which is an important step to realize vehicle positioning. For the special environment where there is no GPS signal in the underground parking lot, accurate and efficient scene recognition can provide an important matching basis for tasks such as car finding and positioning in the underground parking lot. The traditional indoor scene recognition method is to achieve image acquisition through a fixed camera, but for the underground parking lot to find a car, the user often shoots at an unfixed angle, which makes the captured image different from the one used to construct the atlas, resulting in incompatibility. To solve this problem, the patent of the present invention...

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): G06V20/52G06V10/44
Inventor 王相龙严忠贞朱信远徐志刚周可薇刘春陈豪
Owner HUBEI UNIV OF TECH
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