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

Infrared weak and small target segmentation method and device and medium

A weak and small target, infrared technology, applied in the field of image processing, can solve the problem of few segmentation methods of infrared weak and small targets, and achieve the effect of meeting the real-time requirements of the project, fast calculation speed, and ensuring effective segmentation

Active Publication Date: 2022-05-10
CALCULATION AERODYNAMICS INST CHINA AERODYNAMICS RES & DEV CENT
View PDF18 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, most of the infrared target segmentation methods are still developed from the visible light image processing technology, and there are still relatively few segmentation methods for small and weak infrared targets.

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 weak and small target segmentation method and device and medium
  • Infrared weak and small target segmentation method and device and medium
  • Infrared weak and small target segmentation method and device and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Embodiment 1: a kind of infrared dim and small target segmentation method, comprises steps:

[0054] S1, calculate the statistical histogram of the infrared image, perform histogram transformation processing, filter out the extreme value noise points in the image, and obtain the preprocessed image;

[0055] S2, calculating the local background mean value of the infrared image through pseudo-two-dimensional CFAR processing, reducing the interference of the target and noise on the background mean value;

[0056] S3, subtracting the local background mean value from the preprocessed infrared image in two directions of row and column to obtain the local energy value of each pixel, and obtain the image energy distribution map, and enhance the signal-to-noise ratio of the target;

[0057] S4, for the image energy distribution map, use the "back" type sliding window to obtain the local threshold to complete the adaptive threshold acquisition, which can effectively protect weak ...

Embodiment 2

[0059] Embodiment 2: On the basis of Embodiment 1, in step S1, the transformation process includes linear stretching.

Embodiment 3

[0060] Embodiment 3: On the basis of Embodiment 1, in step S2, sub-steps are included: first perform CFAR-like calculation on the image in the horizontal direction to obtain the row local background mean value, and then perform CFAR-like calculation in the vertical direction to obtain the column The local background mean, using the formula:

[0061]

[0062] in, for The local background mean of the point, X p / Y p for the row / column direction with Point as the center of the slide box N The gray mean value of effective pixels, for the horizontal / vertical frame The equivalent gray value of an effective pixel.

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 weak and small target segmentation method and device and a medium, and belongs to the field of image processing, and the method comprises the steps: S1, calculating an infrared image statistical histogram, carrying out histogram transformation processing, filtering extreme noise points in an image, and obtaining a preprocessed image; s2, calculating a local background mean value of the infrared image through pseudo two-dimensional CFAR processing; s3, subtracting a local background mean value from the preprocessed infrared image according to two directions of rows and columns to obtain a local energy value of each pixel point, and obtaining an image energy distribution diagram; s4, for the image energy distribution diagram, acquiring a local threshold by using a sliding window to complete adaptive threshold acquisition; and S5, performing target segmentation on the image according to the obtained local threshold to obtain a segmentation result. According to the method, the infrared small and weak target detection probability, reliability and real-time performance can be improved.

Description

technical field [0001] The present invention relates to the field of image processing, and more specifically, to a method, device and medium for segmenting small and weak infrared targets. Background technique [0002] Infrared target detection, as one of the key technologies of the infrared detection system, is a passive passive detection technology with good stealth performance and anti-interference ability, which has been widely used in the field of national defense and military affairs. Target segmentation, as an important part of target detection, strongly affects the infrared target detection effect. Due to the significant attenuation of infrared radiation energy over distance and the low contrast and signal-to-noise ratio of infrared targets, small infrared targets are easily submerged in background clutter and sensor noise. In addition, considering the limitations of application scenarios, the computing resources of the detection system are often limited, and the al...

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): G06T7/136G06T5/40
CPCG06T7/136G06T5/40G06T2207/10048
Inventor 赵杨曹东王海波杨阳刘林岩卢德勇
Owner CALCULATION AERODYNAMICS INST CHINA AERODYNAMICS RES & DEV CENT
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