An automatic selection method of minimum image set considering topological geometric multi-element constraints
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A geometric element and multi-element technology, applied in the field of image matching, can solve the problem of low image matching efficiency, achieve fast matching, and solve high time-consuming effects
Active Publication Date: 2021-12-14
CHINA UNIV OF MINING & TECH (BEIJING)
View PDF6 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0006] The purpose of the present invention is to design a minimum image set that takes into account the constraints of topological geometry and multi-element constraints to solve the problem of low image matching efficiency due to the large amount of data redundancy in the massive short-baseline, high-overlapping, and multi-angle image sets acquired by the mobile remote sensing platform. Adapt to the preferred method, optimize the data structure
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach
[0034] by Figure 2A ~ D, image 3 , Figure 4 and Figure 5 For example, the implementation process of the present invention will be described in detail. The specific embodiments are as follows:
[0035]Step 1: Use the moving remote sensing platform to take the instant auxiliary data (including position, posture), and the image size of the camera determine the coverage of each image, and constructs an image adjacent matrix G = (V, E) by analyzing the overlap relationship of the image. : V = {1, 2, 3, ..., n} represents the image set, n is the total number, E = {{I, J} (T ij = 1, 1 ≤ i ≤ N, 1≤j ≤ N)}, T ij = 1 indicates video V i And video V j To the neighbor relationship. Fig. 2 (a) shows an adjacent matrix G = (V, E) between the total number N = 11. Among them, V = {1, 2, 3, 4, ..., 11}, matrix [1 line, 2 column] = 1 indicates video V 1 And video V 2 To the neighbor relationship, matrix [1 line, 3 column] = 0 indicates video V 1 With video V 3 For non-adjacent relationships, it is p...
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
This patent discloses an automatic optimization method for the smallest image set that takes into account the constraints of topological and geometric multi-factors: first, the coverage of each image is determined by using the auxiliary data (including position, attitude, etc.) , establish the image adjacency matrix; secondly, based on the image adjacency matrix, extract the topological geometric elements related to the stereo image matching stability, such as base-height ratio, overlapping degree, image intersection angle, etc., and establish the topological geometric elements and the stereo image matching stability Third, extract image factors that can reflect image quality, such as blurriness, texture complexity, etc., and establish the functional relationship between each image factor and the number of feature extraction and its spatial distribution; then, combined with the above research results, establish Taking into account the comprehensive functional relationship between multi-topological geometric elements, image factors and the number of adjacent images, the importance weight of the image is judged; finally, with the minimum N-eye vision as the constraint condition, the necessity of each image participating in the matching is sequentially judged, and the redundancy is eliminated Image, the minimum image set that meets the stability requirements of multi-view image matching is selected.
Description
technical field [0001] The invention belongs to the field of image matching, and in particular relates to an adaptive optimization method for a minimum image set taking into account topological geometry multi-element constraints. Background technique [0002] The rapid development of mobile remote sensing platforms has made it easier and cheaper for people to obtain remote sensing images. Mount sensors such as digital cameras, video cameras, and tilt cameras on mobile platforms such as drones and vehicles, and indirectly restore the three-dimensional structure of objects in the survey area through multi-view image matching. And other fields have a very broad application prospect, which has greatly promoted the development of geographic national conditions monitoring technology. However, considering the existence of errors such as POS system error and camera shake of the mobile remote sensing platform, in order to obtain complete range and detailed ground object information,...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.