Multi-view remote sensing image stereo reconstruction method based on disparity maps and key points

A remote sensing image and three-dimensional reconstruction technology, which is applied in image data processing, character and pattern recognition, 3D modeling, etc., can solve problems such as poor calculation reliability, inability to adapt to reconstruction requirements, and poor image quality, so as to improve accuracy Effect

Active Publication Date: 2019-09-13
XIDIAN UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention solves the shortcomings of poor image pair quality, long reconstruction time, poor reliability of disparity calculation for different targets, inabilit

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
  • Multi-view remote sensing image stereo reconstruction method based on disparity maps and key points
  • Multi-view remote sensing image stereo reconstruction method based on disparity maps and key points
  • Multi-view remote sensing image stereo reconstruction method based on disparity maps and key points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0049] Refer to attached figure 1 , the steps of the present invention are further described in detail.

[0050] Step 1, select image pairs.

[0051] Input at least 10 images taken by the same satellite in the same area, and each image is combined with other images to form an image pair. Each image in each image pair includes roads, viaducts, buildings, vegetation and ground features Both objects also contain header information.

[0052] The header information includes the normalized focal length of the satellite camera corresponding to the input image, the position of the optical center when the input image is captured, the deflection angle of satellite shooting, and the time of satellite shooting.

[0053] From all the image pairs, select the image pairs with the difference between the satellite shooting deflection angle greater than 5° and less than 45°...

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 multi-view remote sensing image three-dimensional reconstruction method based on disparity maps and key points, which mainly solves the defect of low remote sensing image reconstruction precision in the prior art, and comprises the following implementation steps: (1) selecting an image pair; (2) generating a ground object category label; (3) generating a disparity map fused with the ground object category tags; (4) generating a digital surface model DSM of each image pair; (5) fusing the digital surface model DSM of each image pair; (6) marking key points; (7) optimizing the fused digital surface model DSM; and (8) three-dimensionally reconstructing the three-dimensional model. The reconstruction precision of the remote sensing target of the building and the ground category is improved, the parallax calculation precision requirements of label targets of different ground object categories can be met in a self-adaptive mode, and the reconstruction speed of the remote sensing image is increased.

Description

technical field [0001] The invention belongs to the technical field of image reconstruction, and further relates to a stereoscopic reconstruction method of multi-view remote sensing images based on disparity maps and key points in the technical field of stereoscopic reconstruction of remote sensing images. The invention can be used for three-dimensional reconstruction of more than two optical remote sensing images taken by the same satellite at different angles and at different times. Background technique [0002] Stereo reconstruction is the process of reconstructing three-dimensional information of three-dimensional objects based on single-view or multi-view images, and is a key technology for establishing virtual reality expressing the objective world in a computer. In the field of engineering technology, two or more images taken by the same camera at different angles and at different times are usually used to perform stereo matching on the imaging points in different ima...

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): G06T17/05G06K9/62G06K9/46
CPCG06T17/05G06V10/462G06F18/2155
Inventor 焦李成张梦璇陈悉儿冯雨歆黄钟键屈嵘丁静怡张丹李玲玲郭雨薇唐旭冯志玺
Owner XIDIAN 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