Three-dimensional space building window detection and reconstruction method based on unmanned aerial vehicle (UAV) images

A three-dimensional space and three-dimensional reconstruction technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as deformation and window feature changes, achieve accurate detection and reconstruction, improve the level of detail and visualize the effect

Active Publication Date: 2017-08-25
BEIHANG UNIV
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, only relying on the fine training of features cannot better solve the problem of window feature c

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
  • Three-dimensional space building window detection and reconstruction method based on unmanned aerial vehicle (UAV) images
  • Three-dimensional space building window detection and reconstruction method based on unmanned aerial vehicle (UAV) images
  • Three-dimensional space building window detection and reconstruction method based on unmanned aerial vehicle (UAV) images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to better understand the technical solutions of the present invention, the implementation manners of the present invention will be further described below in conjunction with the accompanying drawings.

[0038] Flow chart of the present invention is as figure 1 Shown, the present invention a kind of three-dimensional space building window detection reconstruction method based on UAV image, its specific implementation steps are as follows:

[0039] Step 1: Scene image preprocessing

[0040] First, based on the multi-view image of the target building taken by the UAV, the 3D model of the scene is obtained using 3D reconstruction tools such as CMP-MVS and Pix4Dmapper. According to the normal direction and curvature of the grid, the 3D grid of the building wall in the scene is segmented and extracted, and the 3D support plane P fitted by the least square method is calculated and obtained. Calculate the Euclidean distance d between the surface point of the 3D grid...

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

A three-dimensional space building window detection and reconstruction method based on unmanned aerial vehicle (UAV) images includes the steps of firstly, pre-processing a scene image; secondly, performing Canny edge detection on a texture image; thirdly, establishing a Markov random field and a corresponding energy function for grid distribution of the wall; and fourthly, performing three-dimensional space mapping for two-dimensional coordinates of a detected wall window region and a three-dimensional plane of the wall. Through the above steps, the detection method combines the three-dimensional space information of a building with image information, can eliminate the influence brought by the occlusion, deformation and other structural difference change of a window in the two-dimensional image, can accurately position and reconstruct the structure of the window in a three-dimensional space, and has practical application values in other image processing fields such as target tracking, three-dimensional reconstruction, scene simulation and the like.

Description

[0001] (1) Technical field [0002] The invention relates to a three-dimensional building window detection and reconstruction method based on drone images, belonging to the fields of computer vision and digital image processing. It has broad application prospects in the fields of target recognition and 3D reconstruction. [0003] (2) Background technology [0004] The fine reconstruction of buildings based on geometric structure semantics is one of the key technologies for smart city monitoring. Related technical applications include high-realistic urban scene simulation, roaming navigation, and automatic thermal radiation detection (such as hot spot detection, energy leak location, thermal image generation). These applications all need to obtain detailed structural information of the building wall, and the most critical element is the position and size of the windows on the wall. However, different types of windows have various changes in internal characteristics, such as si...

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): G06T17/00G06T7/13
CPCG06T7/13G06T17/00G06T2207/10016G06T2207/20081
Inventor 熊希贤白相志周付根
Owner BEIHANG UNIV
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