House vectorization method for multi-element remote sensing data

A remote sensing data and vectorization technology, applied in the field of image processing, can solve the problems of lack of house post-processing method, low degree of automation, unsatisfactory house extraction results, etc., to achieve fast detection results, avoid trouble and adverse effects, and calculate the amount of less effect

Active Publication Date: 2016-11-09
安徽省(水利部淮河水利委员会)水利科学研究院(安徽省水利工程质量检测中心站)
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing technology needs to set too many thresholds, and the degree of automation is not high
In addition, the existing technology is mainly aimed at the case where the accuracy of the house extraction results is good, and directly post-processes the extraction results, but the house extraction results in practical applications are often not ideal, and there is still a lack of effective post-processing for houses in different types of image data. Approach

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
  • House vectorization method for multi-element remote sensing data
  • House vectorization method for multi-element remote sensing data
  • House vectorization method for multi-element remote sensing data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The content of the present invention will be described below in conjunction with specific embodiments.

[0036] Such as figure 1 and figure 2 As shown, the specific process of a house vectorization method for multivariate remote sensing data described in this embodiment is as follows:

[0037] Step 1. Obtain the house to be processed.

[0038] Such as image 3 As shown, the house described here can be a house candidate point obtained by various means, or it can be a house patch, a house boundary line and other information that can represent the position and shape of the house: for example, using multi-scale segmentation combined with support vector machine Segmented house patches, house point set outlines obtained by using point cloud segmentation technology and α-shapes algorithm, house edge lines obtained by using active contour method, etc.

[0039] Step 2, get the edge of the house.

[0040] Such as Figure 4 As shown, there are two main steps here: one is to...

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 house vectorization method for multi-element remote sensing data. The house vectorization method comprises the following steps of acquiring information which can represent house position and shape and is needed to be processed; obtaining an ordered edge point by eight neighborhood edge tracing, and simultaneously generating a binary image of a house edge, wherein the edge point is 1, and a non-edge point is 0; obtaining two main directions orthogonal to each other of a house by Radon conversion combined with main shaft analysis; partitioning an edge line of the house to three types of edge line segment, namely, a first main direction type, a second main direction type and a non-directional type; accurately positioning edge line segments of the first main direction type and the second main direction type; calculating a corner edge of adjacent edge line segments; and generating a vectorization house boundary line. By the house vectorization method, the troubles of initial point selection and sequence processing and unfavorable influence during the regularization process of the house can be prevented, the influence of a house extraction result error can also be reduced, and house profile information which is relatively consistent with the shape of the house and is effective and regulated can be acquired.

Description

technical field [0001] The invention relates to a building vectorization method for multivariate remote sensing data, belonging to the technical field of image processing. Background technique [0002] As a major geospatial research information, houses (also known as buildings) are of great significance to the update of two-dimensional maps, the construction of smart cities, and the supervision of illegal buildings. The continuous development of remote sensing technology makes it possible to automatically vectorize and extract house information from remote sensing data. [0003] Multivariate remote sensing data include: image data, LiDAR data, DEM, DSM and other data. Due to the interference of various factors, the house patches (edge ​​lines) currently extracted from multivariate remote sensing data often do not match the actual shape of the house, and it needs to be post-processed - denoising, regularization, etc. [0004] The building outline regularization method discl...

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): G06K9/00
CPCG06V20/176
Inventor 孙金彦王春林钱海明黄祚继周杰宋强
Owner 安徽省(水利部淮河水利委员会)水利科学研究院(安徽省水利工程质量检测中心站)
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