Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image automatic segmentation method and device based on deep learning edge detection

An edge detection and automatic segmentation technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve the problems of severe field jaggedness and missing borders, and achieve the effect of high segmentation accuracy, fine segmentation scale, and simplified difficulty

Pending Publication Date: 2019-12-13
武汉珈和科技有限公司
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes an image automatic segmentation method and device based on deep learning edge detection, which is used to solve the "over-segmentation" or "under-segmentation" in object-oriented segmentation and the large number of boundaries caused by the blurred boundaries of ground objects in deep semantic segmentation models. Missing and serious field jagged problems

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
  • Image automatic segmentation method and device based on deep learning edge detection
  • Image automatic segmentation method and device based on deep learning edge detection
  • Image automatic segmentation method and device based on deep learning edge detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention proposes an image automatic segmentation method and device based on deep learning edge detection, starting from the depth edge detection algorithm, using the trained HED edge detection model to perform edge detection on remote sensing images, and through a series of post-processing operations such as binary , edge extraction and simplification, etc., to obtain accurate image segmentation results. This method does not need to adjust the segmentation parameters, and can more accurately determine the boundary of the segmented object.

[0043] In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only some, not all, embodiments of the presen...

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 provides an image automatic segmentation method and device based on deep learning edge detection. The method comprises the steps of drawing a certain number of training samples accordingto a high-resolution remote sensing image; training an HED edge detection model through the training sample; performing edge detection on the remote sensing image to be segmented by using the trainedHED edge detection model to generate an edge probability graph; performing post-processing on the edge probability graph to generate a vector polygon; and simplifying the vector polygon to obtain animage segmentation result of the remote sensing image to be segmented. According to the image segmentation method provided by the invention, parameters do not need to be adjusted, the segmentation accuracy is higher, automatic operation can be realized, and the image segmentation efficiency is high.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image segmentation, and in particular relates to an image automatic segmentation method and device based on deep learning edge detection. Background technique [0002] With the increasing abundance of high-resolution remote sensing data sources at home and abroad, especially the increase of some domestic sub-meter satellite sensors, such as Gaofen-2 and Gaofen-9 satellites, the price of high-resolution remote sensing images has been greatly reduced. High-resolution remote sensing data are increasingly being used in land and resources census, crop classification, disaster monitoring and other fields. While high-resolution images provide rich textures and details, they also pose great challenges to image segmentation algorithms. Because the phenomenon of "same object with different spectrum, different object with same spectrum" between pixels is more serious than low-resolution images, the a...

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): G06T7/13G06T7/136
CPCG06T7/13G06T7/136G06T2207/10032G06T2207/20152
Inventor 杨泽宇王艳杰
Owner 武汉珈和科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com