Line element intelligent simplification method and device based on tracking type grid subdivision

A line element and subdivision technology, applied in the field of intelligent simplification of line elements based on tracking grid subdivision, can solve problems such as inapplicable intelligent simplification applications, and achieve high intelligence level, strong universality and versatility , the effect of good compatibility

Pending Publication Date: 2020-11-03
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problem that the current spatial subdivision and sample construction methods are not suitable for the application of intelligent simplification of line elements based on the deep learning model of image processing, the present invention proposes a method and device for intelligent simplification of line elements based on tracking grid subdivision

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
  • Line element intelligent simplification method and device based on tracking type grid subdivision
  • Line element intelligent simplification method and device based on tracking type grid subdivision
  • Line element intelligent simplification method and device based on tracking type grid subdivision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] Such as figure 1 As shown, an intelligent simplification method for line features based on tracking grid division, including:

[0076] Step 1. Determine the scales before and after simplification, extract the line elements before and after simplification from the existing map synthesis results, and continuously construct subdivision grids along the direction of the front line elements after simplification;

[0077] Step 2. The unique and continuous partial arcs of simplified front-line elements contained in the subdivision grid are regarded as subdivision arcs;

[0078] Step 3. Determine the simplified subdivision arc based on the subdivision grid and the subdivision arc before simplification;

[0079] Step 4, converting the local arc segments before and after the simplification of the subdivision grid into raster images, and using the paired raster images as learning samples;

[0080] Step 5. Select an image processing deep learning model, and use the raster images b...

Embodiment approach

[0114] Step 7.1.1, use the edge detection operator to extract the predicted simplified result image Im g (k) the outer contour, get the contour image IM g ; As a possible implementation, the canny operator is used to extract the outer contour of the predicted simplification result image;

[0115] Step 7.1.2, traverse all the pixels of the four boundaries of the contour image to determine the position of the starting and ending pixels of the grid curve; specifically, IM g [i,j]∈{IM g [1,u],IM g [sn,u],IM g [u,1],IM g [u,sn]; u∈[1,sn]}, that is, IMg[i,j] is the pixels on the four boundaries, where IM g is the contour image (matrix), IM g [1,u],IM g [sn,u],IM g [u,1],IM g [u, sn] are the four boundaries of the contour image; if IM g [i,j]=0, and j=1, and there is IM g [i ±1,j]>0 or IM g [i,j±1]>0, then IM g [i, j] is the starting pixel of the line element; if IM g [i,j]=0, and j≠1, and there is IM g [i±1,j]>0 or IM g [i,j±1]>0, then IM g [i, j] is the end pixel o...

Embodiment 2

[0188] On the basis of the method described in Example 1, as Figure 15 As shown, the present invention also discloses an intelligent simplification device for line elements based on tracking grid division, including:

[0189] The subdivision grid building module is used to determine the scale before and after simplification, extract the line elements before and after simplification from the existing map synthesis results, and continuously construct the subdivision grid along the direction of the front line elements after simplification;

[0190] The first subdivision arc determination module is used to use the unique and continuous partial arc of the simplified front line elements contained in the subdivision grid as the subdivision arc;

[0191] The second subdivision arc determination module is used to determine the simplified subdivision arc based on the subdivision grid and the pre-simplification subdivision arc;

[0192] The raster image conversion module is used to con...

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 line element intelligent simplification method based on tracking type grid subdivision. The method comprises the steps of continuously constructing subdivision grids in the direction of line elements before simplification; taking a unique and continuous local arc section of the simplified front line element contained in the subdivision square as a subdivision arc section;determining a simplified subdivision arc section based on the subdivision grids and the subdivision arc section before simplification; converting the local arc sections before and after simplification of the subdivision of the subdivision grids into grid images, and taking the paired grid images as learning samples; utilizing the grid images before and after simplification in the learning samplesto train a deep learning model; converting the local arc sections of the to-be-simplified line elements subdivided by the subdivision grids into grid images, inputting the grid images into the trained deep learning model, and predicting the simplified grid images; and converting and combining the predicted grid images to obtain simplified line elements. The invention further discloses a line element intelligent simplification device based on tracking type grid subdivision. According to the method, the line element intelligence and simplification are realized by using the image processing deeplearning model.

Description

technical field [0001] The invention belongs to the technical field of intelligent synthesis of line elements in spatial data processing, in particular to a method and device for intelligent simplification of line elements based on tracking grid division. Background technique [0002] Line feature simplification is an important research content and one of the classic research problems in spatial data processing and automatic map synthesis. The process of simplification of line elements is very complicated, and it is necessary to comprehensively consider multiple factors such as spatial cognition and geographical features, and to selectively perform operations such as trade-offs, shifts, generalizations, and exaggerations for vertices, bends, and targets at different levels of geographic objects. Therefore, it is extremely difficult to simplify the process of clear, accurate and complete abstract lines. However, the intelligent simplification idea of ​​using intelligent meth...

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): G06K9/46G06K9/62G06N3/04G06T11/20G06F17/11
CPCG06T11/203G06F17/11G06V10/44G06N3/045G06F18/214
Inventor 武芳杜佳威朱丽巩现勇殷吉崇行瑞星刘呈熠余林怡
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
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