Infrared weak and small target detection method based on reweighted low-rank and enhanced sparsity
A weak target and infrared technology, applied in the field of image processing, can solve the problems of detection failure, false alarm rate increase, detection rate decrease, etc., and achieve the effect of overcoming low detection rate, large amount of calculation, and fast processing speed
Active Publication Date: 2021-09-28
XIDIAN UNIV
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although this method can realize weak and small target detection, the disadvantage of this method is that in the case of cloudy sky background or mountain background, the background prediction is not accurate, and the improved Tri edge extraction operator is not very good. Extract background edge information, resulting in many false targets when the target is identified, and in severe cases, the detection will fail
Although this method can achieve target detection, the disadvantage of this method is that in the case of low signal-to-noise ratio, because the weak and small targets are not obvious, the target cannot be detected by using this method, resulting in a decrease in the detection rate.
Even some strong backgrounds are falsely detected as targets, resulting in an increase in the false alarm rate
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] The present invention will be further described below in conjunction with the accompanying drawings.
[0032] Refer to attached figure 1 , the concrete steps of the present invention are described as follows:
[0033] Step 1, get infrared image data:
[0034] Extract a frame of infrared image with sky clouds or desert as the background from the infrared image taken by the infrared sensor;
[0035] Step 2, perform slice imaging on the infrared image:
[0036] (2a) Use a window with a fixed size of 50*50 and a step size of 10 to slide on the infrared image;
[0037] (2b) Stretch the infrared image block obtained by sliding each time into a column vector;
[0038] (2c) Arranging all the column vectors according to the sliding order to form an infrared sheet matrix;
[0039] Step 3, using the low-rank sparse formula to construct a reweighted low-rank and enhanced sparse model:
[0040]
[0041] s.t D=B+T
[0042] Among them, min means to take the minimum value ope...
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
The invention discloses a method for detecting small and weak infrared targets based on reweighted low-rank and enhanced sparseness. The specific steps of the invention are as follows: (1) acquire infrared images; (2) visualize infrared image slices; Weighted low-rank and enhanced sparse model; (4) calculate the target slice matrix with an iterative method; (5) reconstruct the target slice matrix; (6) obtain infrared weak and small target detection images; the present invention can be used for infrared weak and small target detection, can reduce Computational complexity and false alarm rate, improve target detection rate.
Description
technical field [0001] The invention belongs to the technical field of image processing, and further relates to a reweighted low-rank and enhanced sparse infrared faint target detection method in the technical field of target detection. The invention can be used to detect weak and small targets, such as airplanes, missiles, satellites, etc., from infrared images in the infrared band. Background technique [0002] Infrared weak and small target detection is the key technology of infrared search and tracking. Due to the long range of the infrared sensor, the size of the target on the image presented by the infrared sensor becomes extremely small, with only a few to dozens of pixels, and no obvious shape and texture. information. In addition, due to environmental interference, there are serious noise and clutter in infrared images, small targets are often submerged in complex backgrounds, and the signal-to-noise ratio is very low, making it very difficult to detect weak and sm...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00
CPCG06T7/0002G06T2207/10048
Inventor 纠博苏呈浩刘宏伟陈渤王英华
Owner XIDIAN UNIV