Remote sensing image road extraction method based on multi-branch pyramid neural network

The invention discloses a method for extracting complete road information on a remote sensing image by using a convolutional neural network. A multi-branch pyramid neural network is constructed, and low-level position information and high-level semantic information are fully mined through two parall...

Full description

Saved in:
Bibliographic Details
Main Authors ZHANG ZHIYUAN, MENG YIZHUO, WEI XIAOBING, DUNYUDUOJI, LI JUNJIE, ZHANG WEN
Format Patent
LanguageChinese
English
Published 29.01.2021
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online AccessGet full text

Cover

More Information
Summary:The invention discloses a method for extracting complete road information on a remote sensing image by using a convolutional neural network. A multi-branch pyramid neural network is constructed, and low-level position information and high-level semantic information are fully mined through two parallel feature recovery structures and a post-processing technology based on geometric structure analysis and feature point extraction. The problem of road sparsity during road extraction on satellite images and the problem of road breakage caused by shielding of vegetation buildings and the like are solved. According to the method, the sparsity of road distribution and the imbalance of samples are comprehensively considered through sparsity test and design of a new loss function, so that the network pays more attention to sparse and difficult-to-classify road pixels. Meanwhile, aiming at the situation that the road is shielded by vegetation and buildings, the method performs automatic fracturedetection and fracture co
Bibliography:Application Number: CN202011162338