Multi-temporal high-resolution remote sensing image building extraction method based on multi-feature LSTM network

A high-resolution, remote sensing image technology, applied in the field of satellite remote sensing image processing and application, can solve the problems of high misclassification rate, blurred border, low accuracy rate, etc.

Active Publication Date: 2020-08-25
JILIN UNIV
View PDF9 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problems of low accuracy, high misclassification rate, and blurred b

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
  • Multi-temporal high-resolution remote sensing image building extraction method based on multi-feature LSTM network
  • Multi-temporal high-resolution remote sensing image building extraction method based on multi-feature LSTM network
  • Multi-temporal high-resolution remote sensing image building extraction method based on multi-feature LSTM network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] Using 6 photos taken on January 2, 2015, May 15, 2015, September 20, 2015, November 28, 2015, March 25, 2016 and February 28, 2017 (GF-2) Multi-temporal remote sensing images are used as the data source. After image preprocessing of 6 original data, the segmentation method combining HSI color transformation, image segmentation and conditional random field post-processing, Gabor wavelet transform and DSBI index calculation are used. The method extracts the building features of the multi-temporal data of 6 scenes, and finally arranges the extracted multi-temporal building feature bands and the four bands of the original data according to the order of the shooting time of the original satellite data to form a multi-temporal multi-temporal network with 60 bands. Phase building feature set, the feature set is used as the input data of the multi-feature LSTM network to train the multi-temporal building extraction model and obtain the rough extraction result of the building. Af...

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 multi-temporal high-resolution remote sensing image building extraction method based on a multi-feature LSTM network, and belongs to the technical field of satellite remote sensing image processing and application. The method aims to solve the problems of low accuracy, high error rate, fuzzy boundary and the like of a building extraction result of an existing method. According to the invention, a plurality of multi-temporal high-resolution No.2 remote sensing images are used as data sources; building spectral characteristics are extracted by using a method based on HSI color transformation; based on a method of combining graph segmentation and conditional random field post-processing, shape features of a building are extracted, based on a Gabor wavelet transform method, texture information features of the building are extracted, and based on a DSBI index method, index features of the building are extracted. A building characteristic set with 60 characteristicwave bands is formed by the extracted spectrum, shape, texture and index characteristics of the multi-temporal building, a manufactured building sample and a label are sent into an LSTM network to obtain a building coarse extraction result, and a final result is obtained after morphological processing.

Description

technical field [0001] The invention belongs to the technical field of satellite remote sensing image processing and application. Background technique [0002] Buildings are the most widely distributed feature category in cities, so buildings are one of the important indicators for evaluating urban economic development. With the continuous development of cities and the increasing number of buildings, the manufacturing materials and appearance of buildings are also changing rapidly, resulting in poor accuracy of building extraction results obtained by traditional methods. For a long time, in order to extract the buildings in the city, the method of manually measuring and drawing the topographic map of urban buildings is mainly used for building extraction. Although this method has certain authenticity, the time cost and labor cost of this method are Huge, and the results of building extraction will vary due to the different cognitive abilities of different surveyors and mapp...

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): G06K9/00G06K9/32G06K9/34G06T7/33G06N3/04
CPCG06T7/33G06T2207/10032G06V20/176G06V10/25G06V10/267G06N3/044G06N3/045
Inventor 顾玲嘉王钰涵任瑞治
Owner JILIN UNIV
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