Segmented SFM three-dimensional reconstruction method

A 3D reconstruction and segmented technology, applied in the field of segmented SFM 3D reconstruction, can solve problems such as inability to reconstruct, affecting reconstruction quality, and 3D scene reconstruction errors

Pending Publication Date: 2020-07-07
西安因诺航空科技有限公司
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the application of UAVs in a large-scale scene, it is inevitable that there will be a long straight flight with a single flight belt. Due to the influence of image noise, the drift error will continue to accumulate with the increase in the number of images, which will affect the reconstruction quality, resulting in 3D scene reconstruction errors and cannot be reconstructed. And other issues

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
  • Segmented SFM three-dimensional reconstruction method
  • Segmented SFM three-dimensional reconstruction method
  • Segmented SFM three-dimensional reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention is further described below in conjunction with accompanying drawing:

[0030] see Figure 1 to Figure 3 , the method first extracts the SIFT features of each image for feature matching. Secondly, according to the GPS coordinates, it is judged whether the scene needs to be segmented. Then the entire image sequence is divided into multiple sub-image sets, and the global SFM method is used to estimate the camera pose and scene point cloud of the sub-image sets respectively. Finally, the reconstruction results of the sub-image sets are combined to obtain the camera pose and scene point cloud of the entire scene.

[0031] The present invention specifically comprises the following steps:

[0032] Step 1: First extract the SIFT feature points of each image, then establish the adjacent image pair ij of image i and its adjacent image j according to the GPS coordinates, perform feature point matching on ij, and obtain the initial matching result, and fina...

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 segmented SFM three-dimensional reconstruction method, and the method comprises the following steps: 1, extracting a feature point of each image, and carrying out the featurepoint matching; 2, judging whether the image sequence needs to be segmented; 3, dividing the image sequence into a plurality of sub-image sets; 4, respectively estimating a camera attitude and a scene point cloud for each sub-image set by using a global SFM method; and 5, according to the GPS information, splicing and combining all the sub-image sets. According to the method, the problems that athree-dimensional scene of large-data-volume single-air-strip long-straight-line flight is wrong in reconstruction and cannot be reconstructed are solved.

Description

technical field [0001] The invention belongs to the application field of unmanned aerial vehicle data, and in particular relates to a segmented SFM three-dimensional reconstruction method. Background technique [0002] With the gradual increase in the demand for acquiring spatio-temporal information of large-scale scenes, UAV (Unmanned Aerial Vehicle, UAV) aerial photography has gradually attracted attention. Compared with traditional aerial photography, UAV aerial photography is easy to operate, low in price, short in operation cycle, and can obtain high-resolution images at low altitude, which has advantages that traditional aerial photography and remote sensing mapping do not have. [0003] Structure From Motion (SFM), that is, to determine the spatial and geometric relationship of the target through the movement of the camera, is a common method for 3D reconstruction. The biggest difference between it and the traditional 3D reconstruction method is that it only needs an...

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): G06T17/00G06T7/33
CPCG06T17/00G06T7/33G06T2207/10004G06T2207/10028
Inventor 香玫元
Owner 西安因诺航空科技有限公司
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