Geometric feature-based visual reconstruction method

A technology of geometric features and geometry, applied in 3D modeling, image data processing, instruments, etc., can solve the problems of complex calculation and large consumption of computing and battery resources, and achieve reduced calculation and storage overhead, convenient use, high matching accuracy and high matching accuracy. The effect of scene reconstruction accuracy

Active Publication Date: 2017-06-13
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, traditional visual reconstruction positioning methods are usually point-based, that is, pixel-level calculations, which are complex and consume a lot of computing and battery resources.

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
  • Geometric feature-based visual reconstruction method
  • Geometric feature-based visual reconstruction method
  • Geometric feature-based visual reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0027] A visual reconstruction method based on geometric features proposed by the present invention, such as image 3 As shown, geometric features are used for matching between scenes. When reconstructing a 3D scene, each pixel is not reconstructed, but the geometric blocks of each scene, such as rectangular blackboards and posters, are extracted first, and the 3D scene reconstruction of a single image is performed based on the geometric blocks, and then used The geometric data of the geometric block (such as the length and width of the blackboard, etc.), and the pixel information of the geometric block (such as the black color of the blackboard) are used as features to match multiple pictures, and finally complete the 3D scene reconstruction. This scheme only uses geometric blocks instead of pixels to complete scene reconstruction, which greatly reduces computing and storage costs, and can achieve high matching accuracy and even scene reconstruction accuracy. The specific im...

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 geometric feature-based visual reconstruction method. According to the method, reconstruction is not performed for each pixel during 3D scene reconstruction; instead, firstly objects (geometric components) with geometric features in each scene are extracted, and the 3D scene reconstruction of a single scene picture is performed based on geometric blocks; secondly a plurality of scene pictures are matched by using the geometric features such as the sizes, the pixel information and the like of the geometric blocks as matching features; and finally the 3D scene reconstruction is finished. According to the scheme, the scene reconstruction is finished only by utilizing the geometric features instead of pixels, so that the calculation and storage overheads are greatly reduced and very high matching precision and scene reconstruction precision can be achieved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a visual reconstruction technology for extracting and matching geometric features of a target scene. Background technique [0002] Map reconstruction and localization have always been one of the important technologies in the field of computer vision, and have received extensive attention from industry and academia in the past decade. The prior art "Google Map Indoor, https: / / www.google.com / maps / about / partners / indoormaps" discloses a Google Map Indoor (GMI), which is an indoor positioning system launched by Google based on Wi-Fi signals for triangulation, and are not widely used. The main reason is that the positioning accuracy of the Wi-Fi signal is not ideal and cannot reach the commercial level. At the same time, it is impossible to draw a visual map and provide users with an easy-to-understand positioning method. To overcome these shortcomings, the prior ...

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): G06T17/10
Inventor郝洁王然
OwnerNANJING UNIV OF AERONAUTICS & ASTRONAUTICS