Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Infrared image background suppression method based on unsupervised kernel regression analysis

An infrared image and background suppression technology, applied in the field of infrared image background suppression, can solve problems such as requiring prior knowledge and poor adaptability, and achieve good nonlinear data prediction ability, good background effect, and good local adaptive prediction ability. Effect

Inactive Publication Date: 2009-11-18
HARBIN INST OF TECH
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides an infrared image background suppression method based on unsupervised kernel regression analysis in order to solve the technical problems that require prior knowledge and poor adaptability in the field of infrared image background clutter suppression

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
  • Infrared image background suppression method based on unsupervised kernel regression analysis
  • Infrared image background suppression method based on unsupervised kernel regression analysis
  • Infrared image background suppression method based on unsupervised kernel regression analysis

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0018] Specific implementation mode one: combine figure 1 Describe this embodiment, the steps of this embodiment are as follows:

[0019] Step 1. Set the sliding window for background prediction; the sliding window adopts a double-window mode to predict the background clutter, and the sliding window is composed of inner window B and outer window A; inner window B is located at the center of the sliding window, and inner window B’s The center is the center test sample O, and the inner window B is used to protect the information of the center test sample O located in the center of the sliding window. The area of ​​the inner window B outside the center test sample O is equivalent to the protection area to prevent the test sample O from being the target pixel. In the process of selecting background clutter samples, the samples related to the target are selected, so the protection area is generated; the outside of the inner window B of the sliding window is the outer window A, and ...

specific Embodiment approach 2

[0025] Specific implementation mode two: combination figure 2 This embodiment is described. The first difference between this embodiment and the specific embodiment is that if the central test sample O of the inner window B currently being processed is located at the edge of the infrared image C, the samples of the missing part in the sliding window are obtained by mirror symmetry. , that is to use mirror symmetry to obtain the gray value of missing pixels. Other steps are the same as in the first embodiment.

specific Embodiment approach 3

[0026] Specific embodiment three: the difference between this embodiment and specific embodiment one is that the steps for obtaining the unsupervised kernel regression equation in step three are as follows:

[0027] The regression estimation formula is as follows:

[0028] the y i =z(x i )+ε i , i=1, ..., P, (1)

[0029] where x i It is a 2x1-dimensional vector, representing the coordinates of the two-dimensional space, y i Represents the corresponding image gray value; z(x i ) is called the regression function, ε i For random error or random disturbance, it is a distribution with x i An irrelevant random variable, which is a normally distributed random variable with a mean of 0; the z(x i ) is expanded in the neighborhood, the following formula can be obtained:

[0030] z(x i )=β 0 +β 1 T (x i -x)+β 2 T vech{(x i -x)(x i -x) T}+... (2)

[0031] The definition of vech( ) is the vectorization of the lower triangular part of the symmetric matrix, with a 2×2 s...

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 an infrared image background suppression method based on unsupervised kernel regression analysis, belonging to the image processing field. The infrared image background suppression method solves the technical problems that priori knowledge is needed and self-adaptability is poor in the field of infrared image background clutter suppression. Firstly, a sliding window is set to predict background, and Gaussian function is determined to serve as kernel function for unsupervised kernel regression analysis; a background predicting clutter sample is substituted in the function to calculate unsupervised kernel regression equation, and a central test sample (O) is input into the unsupervised kernel regression equation so as to obtain the predicted value of the central test sample (O); then, the central test sample (O) value subtracts the predicted value; the sliding window moves, the above process is repeated until the whole image is processed, and a background suppression result image is output. The invention can effectively improve target detectability and positioning accuracy of an infrared target recognition and tracking system, an infrared image monitoring system, etc.

Description

technical field [0001] The invention relates to a method for suppressing an infrared image background, belonging to the field of image processing. Background technique [0002] In the infrared automatic target detection system, in order to find the target as early as possible, make the infrared guidance system have enough reaction time and improve the early warning distance of defensive weapons, it is required to be able to detect the target at a very long distance, so that it can be found as early as possible Target. When the detection distance and imaging field of view increase, even if the target itself is large, it will only appear as a few pixels or even less than one pixel in the imaging plane, which is called a small target. At this time, the detectable signal is relatively weak, especially under the interference of non-stationary undulating background, the target is even submerged by a large amount of complex noise (clutter), and the image signal-to-noise ratio is e...

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): G06T5/00G06T7/00
Inventor 谷延锋王晨张晔
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com