Stereo image pair selection method based on minimum spanning tree
A stereoscopic image pair and spanning tree technology, applied in image analysis, image enhancement, image data processing, etc., can solve the problem of inability to guarantee reconstruction accuracy and completeness, unfavorable large-scale 3D terrain production and update, and unfavorable 3D terrain surveying and mapping production and application issues to achieve the effect of shortening the 3D reconstruction time, reducing redundant calculations, and shortening the time
Active Publication Date: 2020-12-04
WUHAN ENG SCI & TECH RESINST
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
If there are too many stereo image pairs, although the reconstruction accuracy and integrity can be guaranteed, it will lead to a huge amount of 3D reconstruction time, which is not conducive to the production and update of large-scale 3D terrain
If the number of stereo image pairs is too small, although the 3D reconstruction time can be greatly shortened, the reconstruction accuracy and integrity cannot be guaranteed, which is not conducive to the production and application of 3D terrain surveying and mapping
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0039] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:
[0040] A method for selecting a stereo pair based on a minimum spanning tree in the present invention, such as figure 1 As shown, it includes the following steps:
[0041] Step 1: According to the input image set and the corresponding camera parameters and external orientation elements POS of each image in the image set, the camera parameters include camera focal length, pixel size, and camera distortion correction parameters; baseline constraints and image plane normal vector constraints are used , feature matching constraints and intersection angle constraints. In the input image set, select suitable candidate images to be matched for each image to form a candidate stereoscopic image set. The specific method is:
[0042] Assume that in the input image set, the number of images is N; if all the images in the image set form a stereo pair, then ...
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
Login to View More Abstract
The invention relates to a stereopair selection method based on a minimal spanning tree; the method comprises the following steps; 1, automatically building a proper candidate stereo image set according to an input image set and camera parameters and elements of exterior orientation POS corresponding to each image; 2, building a graph G (V, E), and calculating the weight value of the correspondingedge according to the plane coverage condition of each candidate stereo image on an overlapping area; 3, using the minimal span tree algorithm to select the edge set with the minimum weight value asthe stereopair selection result. The method can greatly shorten the reconstruction time while ensuring the reconstruction precision and reconstruction completeness, and can be applied to land plotting, long range three dimensional modeling and virtual reality.
Description
technical field [0001] The invention relates to the field of stereo image pair selection in photogrammetry, in particular to a method for selecting stereo image pairs based on a minimum spanning tree. Background technique [0002] With the continuous advancement of sensor hardware, different types of optical remote sensing platforms have emerged, such as satellites, aerial photography aircraft, drones, airships, and surveying and mapping vehicles. These remote sensing platforms are capable of taking multi-scale, multi-angle, multi-resolution, and multi-coverage massive images for surveying and mapping production and 3D modeling. [0003] Multi-view image dense matching technology can automatically reconstruct 3D terrain based on multi-view images. The 3D reconstruction time, 3D reconstruction accuracy and 3D reconstruction completeness of multi-view image dense matching are closely related to the number of stereo pairs. If there are too many stereo image pairs, although th...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T17/00G06T7/593
CPCG06T17/00G06T2207/10012G06T7/593
Inventor 黄旭周刚胡堃高其双蔡刚山
Owner WUHAN ENG SCI & TECH RESINST