Method for generating multi-scale house detection vector diagram

A vector graphics and multi-scale technology, applied in the field of generating multi-scale house detection vector graphics, can solve the problems of inability to meet authoritative data standards, post-processing instability, noise, etc.

Pending Publication Date: 2021-05-18
杭州高斯洪堡科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitation of occluders (such as trees, etc.) near the building, the predicted mask image contains noisy or blurred pixels at the boundary of the b

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
  • Method for generating multi-scale house detection vector diagram
  • Method for generating multi-scale house detection vector diagram
  • Method for generating multi-scale house detection vector diagram

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.

[0024] In describing the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", " The orientation or positional relationship indicated by "outside", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, so as to Specific orientation configurations and operations, therefore, are not to be construed as limitations on the invention.

[0025] Such as figure 1 ...

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 relates to the technical field of multi-scale house detection vector diagrams, in particular to a method for generating a multi-scale house detection vector diagram, which comprises the following steps of: 1, classifying earth surface targets by utilizing an earth surface coverage segmentation network, and performing network jump connection by utilizing skip-connection; 2, generating a house vector diagram by using a house vector diagram generation network, and processing training data according to different scale proportions in order to implicitly learn multi-scale information; 3, carrying out polygon extraction and shape simplification of the house vector diagram by using a Marching Cubes algorithm and a Regulation Building Footprint module provided in an arcpy library of ArcGIS10.4, and meanwhile, solving the problems that corners of a building are incomplete and opposite sides are not parallel. According to the method, multi-scale processing can be carried out on an existing map, multi-scale information is implicitly learned through the neural network, and a multi-scale vector diagram with a good effect is obtained.

Description

technical field [0001] The invention relates to the technical field of multi-scale house detection vector diagrams, in particular to a method for generating multi-scale house detection vector maps. Background technique [0002] Multiscale vector graphics are one of the important measurement products of national cartographic agencies. Today, building extraction from aerial imagery is mostly done with deep convolutional neural networks, where the network predicts buildings as a mask, followed by polygonal adjustments to regularize the boundaries. However, due to the limitation of occluders (such as trees, etc.) near the building, the predicted mask image contains noisy or blurred pixels at the boundary of the building, resulting in unstable post-processing and failing to meet authoritative data standards. Therefore many methods can only be used for small map scale predictions. [0003] However, the resolution of the image will affect the obtained multi-scale map results, tha...

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): G06T11/00G06T7/10
CPCG06T11/00G06T2207/20081G06T2207/20084G06T7/10
Inventor 杨纯周博文
Owner 杭州高斯洪堡科技有限公司
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