Urban rail transit remote sensing image data processing system and method

An urban rail transit and remote sensing image technology, applied in the field of urban rail transit remote sensing image data processing system, can solve the problems of low accuracy and slow speed of buildings, achieve good robustness and generalization, prompt processing speed, The effect of improving prediction accuracy

Active Publication Date: 2021-09-07
全图通位置网络有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] In order to solve the problems of the prior art, the present invention provides a system and method for processing remote sensing image data of urban rail transit, which integrates convolutional neural network and semantic segmentation algorithm to realize building object extraction, and solves the problem of existing deep learning-based Problems such as low precision and slow speed of extracting buildings from remote sensing images

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
  • Urban rail transit remote sensing image data processing system and method
  • Urban rail transit remote sensing image data processing system and method
  • Urban rail transit remote sensing image data processing system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] as attached figure 1 As shown, a processing method of urban rail transit remote sensing image data, comprising the following steps:

[0058] A. Input high-resolution remote sensing images, use feature extraction network to extract backbone features, and build feature pyramids;

[0059] B. Inputting the backbone features into the region recommendation network to predict a suggestion frame that may contain buildings;

[0060] C. Intercept the backbone features according to the suggestion frame, first input the backbone feature into the fully connected network prediction object type, use the border adjustment parameters of synchronous prediction to adjust the suggestion frame as the prediction frame, and then intercept the part from the backbone feature according to the prediction frame Feature map, the convolutional network input to the semantic segmentation module predicts the building mask;

[0061] D. Label the obtained object prediction frame and its building mask o...

Embodiment 2

[0078] This embodiment provides a processing system for urban rail transit remote sensing image data, including a remote sensing image feature extraction module, an area recommendation module, and an object prediction class semantic segmentation module,

[0079] The remote sensing image feature extraction module is used to extract the backbone features of the urban rail transit remote sensing image and construct a feature pyramid;

[0080] The region recommendation module is used to extract features from the feature pyramid using shared convolution to generate a suggestion frame;

[0081] The object prediction class semantic segmentation module is used to generate a prediction frame after convolving the local features extracted from the suggestion frame, and intercept the local features of the prediction frame from the shared feature map and the prediction frame to generate Object mask.

[0082] as attached figure 2 As shown, the remote sensing image feature extraction modu...

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 belongs to the technical field of urban rail transit remote sensing image data processing, in particular to an urban rail transit remote sensing image data processing system and method. The system comprises a remote sensing image feature extraction module, a region recommendation module and an object prediction class semantic segmentation module. According to the system and method, building objectification extraction is realized by fusing a convolutional neural network and a semantic segmentation algorithm, and the problems of low precision, slow speed and the like of remote sensing image building extraction based on deep learning in the prior art are solved.

Description

technical field [0001] The invention relates to the technical field of urban rail transit remote sensing image data processing, in particular to a processing system and method for urban rail transit remote sensing image data. Background technique [0002] The existing methods of extracting buildings from remote sensing images using deep learning algorithms are mainly convolutional neural networks (CNN). The convolutional neural network is an improved algorithm of the fully connected neural network. It changes the input nodes of the neural network from image pixels to features extracted by image convolution and pooling, reducing the number of input nodes of the neural network and reducing the network scale. , suitable for processing two-dimensional image data. [0003] The current use of convolutional neural networks to extract buildings from remote sensing images is mainly divided into two stages. In the first stage, the model is trained, typical buildings are cut from remo...

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): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/24
Inventor 张开婷李俊周立荣蔺陆洲贾蔡祝宏邓平科杨军马长斗张迪
Owner 全图通位置网络有限公司
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