Remote sensing image building extraction method based on foreground perception

An extraction method and remote sensing image technology, which is applied in the field of remote sensing image processing, can solve problems such as multi-scale, recognition errors, and large scale changes of objects, and achieve the effect of enhancing feature recognition capabilities and reducing misidentification

Pending Publication Date: 2022-04-15
杭州市规划和自然资源调查监测中心(杭州市地理信息中心)
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First of all, the scale of objects in high-resolution remote sensing images varies greatly, causing multi-scale problems, making it difficult to locate and identify objects
Secondly, the background in high-resolution remote sensing images is more complex, and the intra-class differences are large, which may easily cause recognition errors
Again, the proportion of foreground in high-resolution remote sensing images is much smaller than that of ordinary images, resulting in the imbalance between foreground and background

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
  • Remote sensing image building extraction method based on foreground perception
  • Remote sensing image building extraction method based on foreground perception
  • Remote sensing image building extraction method based on foreground perception

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to illustrate the technical solution design of the system more clearly and systematically, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. The specific embodiments described here are only used to explain the present invention, and do not limit the protection scope of the present invention.

[0040] Such as figure 1 As shown, a kind of remote sensing image building extraction method based on foreground perception proposed by the present invention comprises the following steps:

[0041] (1) The present invention uses the Gaofen-2 remote sensing image as the input data source, and first performs basic image feature extraction through an improved ResNet backbone network, which includes two residual units and three residual connections, and the network model is as follows figure 2 Shown:

[0042] (a) The first residual unit has the same structure as the traditional resi...

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 remote sensing image building extraction method based on foreground perception, and the method comprises the steps: firstly carrying out the basic image feature extraction of an input image through an improved ResNet network, obtaining a pyramid feature map through a bidirectional FPN network, carrying out the modeling of a foreground and a geographic space scene, associating the foreground with a related context, and carrying out the recognition of the foreground. The incidence relation is utilized to enhance the input feature map, the difference between the foreground feature and the background feature is increased, the distinction degree of the foreground feature is improved, and efficient and accurate automatic extraction of the building in the remote sensing image is achieved.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a method for extracting buildings from remote sensing images based on foreground perception. Background technique [0002] Surface buildings are an important land resource, one of the basic elements of a city, and are closely related to human life. Remote sensing technology is an effective way to carry out dynamic monitoring of large-scale buildings. It has the advantages of wide coverage, strong timeliness, rich information, and few restrictions. played an important role in. With the improvement of computer computing power and the development of artificial intelligence, deep learning has been widely used in computer vision, natural language processing and other fields, as well as in the field of remote sensing image processing. Some results have been obtained in the extraction of buildings from images. [0003] Extracting building informati...

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): G06V20/10G06V10/44G06V10/80G06V10/82G06K9/62G06N3/08G06T7/194
Inventor 施仲添陈晓勇叶梦刘分元俞成郭琛范芹芹焦超峰丁松庆
Owner 杭州市规划和自然资源调查监测中心(杭州市地理信息中心)
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