Remote sensing image semantic segmentation method based on pyramid pooling multistage feature fusion network

A technology of pyramid pooling and feature fusion, applied in biological neural network models, character and pattern recognition, instruments, etc., to achieve improved results

Inactive Publication Date: 2021-02-26
JIANGXI NORMAL UNIVERSITY
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing image semantic segmentation methods have improved or solved the semantic segmentation problem of complex image scenes to a certain extent. Compared with natural images, the featu

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 semantic segmentation method based on pyramid pooling multistage feature fusion network
  • Remote sensing image semantic segmentation method based on pyramid pooling multistage feature fusion network
  • Remote sensing image semantic segmentation method based on pyramid pooling multistage feature fusion network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The present invention will be further described below in conjunction with the accompanying drawings and embodiments. The objects operated by the present invention are medium and high-resolution remote sensing images, which at least contain spectral information of red, green, and blue bands. For training, the proposed model needs a certain number of labeled remote sensing images as training samples. The specific implementation process is illustrated by taking a remote sensing image and its corresponding labeling process as an example. figure 1 The overall processing block diagram of the present invention is given, and the specific implementation steps of the present invention will be described in detail below. Realization of the present invention is divided into five main steps altogether, is respectively:

[0056] Step 1: Preparation of training sample set

[0057] Model training requires a large number of samples. In the present invention, a series of image blocks ar...

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 semantic segmentation method based on a pyramid pooling multistage feature fusion network. The method comprises steps of employing ResNet to extract features, respectively introducing the features extracted at each stage of ResNet into a spatial pyramid pooling structure to extract the multi-scale information of a target, and introducing a double attention module to the last part of feature extraction, and a multi-level feature fusion strategy is adopted to perform feature fusion on the pooled features and the features acquired by the double attention module so that refined classification of the remote sensing images can be realized.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, belongs to remote sensing image surface object classification technology, and in particular relates to a remote sensing image semantic segmentation method based on a pyramid pooling multi-level feature fusion network. Background technique [0002] Remote sensing images have the characteristics of large coverage and intuitive reflection of the surface. The classification of remote sensing images is widely used in land monitoring, environmental monitoring, and map making. [0003] The current mainstream image semantic segmentation methods can be roughly divided into two categories, traditional machine learning methods and deep learning-based methods. The traditional machine learning method uses the color, texture, shape and spatial position relationship of the object to extract features, and then uses clustering, classification and other algorithms to segment the image. However, t...

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): G06K9/00G06K9/34G06K9/62G06N3/04
CPCG06V20/13G06V10/267G06N3/045G06F18/253G06F18/24G06F18/214
Inventor 胡蕾李云洪胡支波翁梦倩
Owner JIANGXI NORMAL UNIVERSITY
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