Remote sensing image road extraction method based on residual network
A remote sensing image and road extraction technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of complex structure and low accuracy of road information extraction, achieve high detection accuracy, reduce the loss of detailed information, and ensure accuracy Effect
Inactive Publication Date: 2019-12-20
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 9 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the above-mentioned deficiencies in the prior art, the method for extracting roads from remote sensing images based on the residual network provided by the present invention solves the problems of complex structure and low accuracy of road information extraction in the prior art
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0039] The specific embodiments of the present invention are described below so that those skilled in the art can understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes Within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are included in the protection list.
[0040] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.
[0041] Such as figure 1As shown, a road extraction method for remote sensing images based on residual network, including the following steps:
[0042] S1. Construct a variant Res-block structure on the basis of the residual network, and construct a coding module through the variant Res-block struct...
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
Login to View More Abstract
The invention discloses a remote sensing image road extraction system and method based on a residual network. A B-DLinkNetPlus network architecture comprising an input layer, a stem block unit, a variant Res-block structure and a DBlockPlus is constructed. A variant Res-block structure is designed on the basis of a residual network and serves as a coding module, the characteristic of gradient backpropagation to a shallow network is improved, and the problem of gradient dispersion is solved. According to the method, the feature fusion of the DBlock and the number of channels of the feature mapare optimized to construct the DBlock Plus unit, so that the size of a network model and the loss of detail information are reduced. According to the remote sensing image road extraction system, three continuous 3 * 3 convolution layer stem block units are adopted, and a B-DLinkNetPlus deep convolution network is constructed by combining hole convolution, so that the remote sensing image road extraction system with high precision and light weight is realized.
Description
technical field [0001] The invention belongs to the technical field of automatic processing of remote sensing images, and in particular relates to a method for extracting roads from remote sensing images based on a residual network. Background technique [0002] As a common and important digital image, remote sensing image is the product of the rapid development of space measurement technology, earth science theory, computer technology, sensor technology and aerospace technology in the 1960s. People can obtain ground information carried by remote sensing images by processing and analyzing them, which has high application value for scientific research or practical life applications. [0003] With the development of remote sensing technology, remote sensing images tend to develop towards high resolution. On the one hand, this high-resolution remote sensing image can provide more detailed feature information for the detection of road areas, such as the color of the target in th...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/182G06N3/045G06F18/214
Inventor 李玉霞童玲彭博范琨龙李振旭司宇杨超
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA