Remote sensing image multi-objective association method

A remote sensing image, multi-target technology, applied in image analysis, image data processing, instruments, etc., can solve the problems that remote sensing imaging cannot accurately estimate target state information, multi-target matching correlation ambiguity, etc., and achieve good affine invariance and Anti-interference, improved timeliness, quick results

Inactive Publication Date: 2014-08-13
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to avoid the deficiencies of the prior art, the present invention proposes a method for multi-target association of remote sensing images, which solves the problem that the current remote sensing imaging cannot accurately estimate the target state information and the ambiguity of multi-target matching associations in large scene images

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
  • Remote sensing image multi-objective association method
  • Remote sensing image multi-objective association method
  • Remote sensing image multi-objective association method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0053] The hardware environment used for implementation is: Pentium-43G computer, 2GB memory, 128M graphics card, and the running software environment is: Mat1ab7.0 and windowsXP. We have realized the new algorithm proposed by the present invention with Matlab programming language. Experiments are carried out using gray-scale images of 6 types of aircraft targets at Haiti airports (from IKONOS satellite images with a resolution of 1 meter and a size of 3000×3000 for some Haiti airports), and the size of each image is 128×128. In addition to scaling, rotating, and affine transforming the image, different levels of Gaussian white noise, occlusion, and brightness changes are added to form multiple groups of 6 types of aircraft targets to be associated.

[0054] Step 1 feature extraction: MSA feature is variable f(μ α,β ) mathematical expectation value: take any combination of two elements in the set {-1,-0.75,-0.5,-0.25,0,0.25,0.5,0.75,1} to form 29 pairs of (α,β) values, and ca...

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 relates to a remote sensing image multi-objective association method. At first, multi-scale auto-convolution (MSA) characteristics of a target image are extracted according to MSA conversion, and a matching cost of any two targets is obtained through calculation of Euclidean distance among the target characteristics, namely similarity measurement is obtained. Multi-objective association in two remote sensing images is considered as two-dimensional distribution, a multi-objective association cost matrix (ACM) is constructed, then practical application is combined, and an objective function is constructed according to the maxim of relevance, namely a global optimization model is constructed. At last, a simulated annealing algorithm is improved, inner loop iterations and outer loop iterations are set, a new self-adaptive temperature updating function is designed, a temperature control mode is improved, and therefore time performance of the algorithm is improved on the basis that association accuracy is guaranteed.

Description

technical field [0001] The invention relates to a method for multi-target association of remote sensing images, which is based on image multi-scale auto-convolution moment (Multi Scale Auto-convolution, MSA) features and simulated annealing optimized multi-target association of remote sensing images. It can be widely used in multi-target detection, recognition, fusion and tracking systems of remote sensing images. Background technique [0002] The previous target association methods mainly refer to the state filter method, which treats the target as a point object and uses the motion characteristics of the target position, speed, and orientation provided by radar data to perform correlation, which is suitable for densely sampled sequence images. For example, in 1989, Shalom Y B proposed a joint probabilistic data association (JPDA) method based on the target centroid and centroid offset. First, the target and the background are segmented, and then the centroid of the target ...

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): G06T7/00
Inventor 李晖晖滑立郭雷杨宁
Owner NORTHWESTERN POLYTECHNICAL 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