Infrared weak and small target detection method based on multi-feature fusion

A multi-feature fusion and weak target technology, which is applied in the field of infrared weak target detection based on multi-feature fusion, can solve the problems of high false alarm rate and low detection rate, and achieve the effect of suppressing the background

Pending Publication Date: 2021-12-21
ZHONGBEI UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the common problems of low detection rate and high false alarm rate of weak and small infrared targets in complex backgrounds, the present invention proposes a detection method for weak and small infrared targets based on multi-feature fusion, which is used for the detection of weak and small infrared targets in infrared images under complex backgrounds, effectively improving Detection accuracy and robustness

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 detection method based on multi-feature fusion
  • Infrared weak and small target detection method based on multi-feature fusion
  • Infrared weak and small target detection method based on multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be further elaborated below in conjunction with accompanying drawing and specific embodiment:

[0025] refer to figure 1 and figure 2 , a method for detecting small infrared targets in complex backgrounds in this embodiment includes the following steps:

[0026] Step 1: Input an infrared image I to be detected with a size of H×W in ;

[0027] Step 2: Put the image I in Convert to grayscale image I;

[0028] Step 3.1: Construct a 19×19 sliding window centered on a pixel point s in the grayscale image I, divided into 9 units, the center unit S 0 The size is 5×5, the size of the background area units S1, S3, S6, and S8 is 7×7, the size of S2 and S7 is 5×7, and the size of S4 and S5 is 7×5, such as image 3 shown;

[0029] Step 3.2: Calculate the pooled brightness of all background area units, that is, the mean value of the gray levels of all pixels in the unit. The specific calculation method is:

[0030]

[0031] Among them, H ij I...

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 provides an infrared weak and small target detection method based on multi-feature fusion, and the method comprises the steps: firstly, enhancing a real target by the gray contrast of the target and a neighborhood background based on the large local gray value of an infrared weak and small target, and suppressing a part of complex background; secondly, detecting the target by calculating the distance between the edge pixel point and the center pixel point of the infrared weak and small target and the covariance of the gray difference by utilizing the characteristic that the gray information of the infrared weak and small target conforms to the two-dimensional Gaussian distribution, and obtaining a first explicit image; thirdly, by means of the characteristic that the similarity between an infrared weak and small target and a neighborhood is low, detecting the target by calculating a similarity factor to acquire a second explicit graph; and finally,performing point multiplication on the first explicit image and the second explicit image, acquiring a final explicit image by fusing various characteristics of the infrared weak and small target, and calculating a simple threshold value for the final explicit image for segmentation to obtain a final detection result. Complex clutters in the infrared image are effectively suppressed, and the weak and small target detection precision is improved.

Description

technical field [0001] The invention relates to the field of infrared image target detection, in particular to a method for detecting infrared weak and small targets based on multi-feature fusion. Background technique [0002] Infrared target detection is one of the core technologies of long-range early warning, precision guidance and other systems, among which infrared dim and small target detection is a classic problem. The main difficulties are: 1) The imaging distance is very far, and the target not only lacks characteristic information in the image but is easily confused with noise; 2) The edge of high-intensity clutter is easily misdetected as the target, which increases the number of false alarms; 3) Both Weak and small objects are often submerged in complex backgrounds, resulting in serious missed detections. Therefore, infrared weak and small target detection in complex background has always been a very challenging task. [0003] At present, there are few research...

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): G06K9/62G06K9/34
CPCG06F18/22G06F18/253
Inventor 蔺素珍武杰禄晓飞李大威余东张海松樊小宇赵亚丽
Owner ZHONGBEI 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