Multispectral infrared image background suppression method based on topology-graph-cut fusion optimization
A background suppression and infrared image technology, which is applied in the field of multi-spectral infrared image background suppression, can solve the problems of high false alarm probability of background suppression results, difficulty in accurately distinguishing between targets and background clutter, and achieve the goal of easy target segmentation and detection Effect
Active Publication Date: 2021-11-02
XIDIAN UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, for complex and changeable non-stationary backgrounds, these methods are difficult to accurately distinguish between targets and background clutter, and are easily affected by parameters such as window size and structural elements, which usually make the false alarm probability of background suppression results higher.
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 1
[0158] An embodiment of the present invention provides a method for suppressing the background of an infrared multispectral image based on topology-graph-cut fusion optimization, such as figure 1 As shown, the method is specifically implemented through the following steps:
[0159] Step 101: Perform local preprocessing on the dual-band infrared images respectively.
[0160] Specifically, the 4-neighborhood operator is used to obtain the local extremum points in the image, and the preprocessing algorithm can be expressed by formula (1).
[0161]
[0162] Among them, u represents an image with a size of M×N, the subscript s represents a certain pixel in the image u, and u s represents the gray value of pixel s; set n s ={w,e,n,s} indicates the four adjacent pixels of pixel s, Then it represents the gray value of pixel s after local preprocessing.
[0163] Step 201: Using topological differential technology to suppress strong undulating edges on the obtained preprocessed ...
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 present invention discloses a multi-spectral infrared image background suppression method based on topology-graph-cut fusion optimization, respectively performing local Patch preprocessing on multi-spectral infrared images to obtain preprocessed images, and according to the topological differential method for the The preprocessed image is suppressed by strong undulating edges to obtain the optimal diffusion coefficient. According to the combination of the obtained optimal diffusion coefficient and the gradient mean filter, the background suppression is performed on the single-band image respectively, and several single-band clutter-suppressed targets are obtained. image; according to the scale area energy theory model, the obtained target images after several single-band clutter suppression are fused to obtain a background suppression result image of multi-spectral fusion; the background suppression result image of the multi-spectral fusion Optimize the image cutting strategy to eliminate the local contour effect of the fused image, and finally obtain the image after background suppression. The invention can effectively suppress the infrared background with high gray level and violent fluctuation contained in the infrared image, and can highlight the target information.
Description
technical field [0001] The invention belongs to the technical field of infrared image processing, and in particular relates to a method for suppressing the background of a multi-spectral infrared image based on topology-graph cut fusion optimization. Background technique [0002] Infrared image background suppression has attracted more and more attention in the field of infrared image processing, because it has potential important applications in infrared weak and small target detection; especially for the detection of small targets in infrared images with complex background and low contrast ; For example, it is extremely difficult to accurately detect small targets in complex sky backgrounds and sea-sky backgrounds; in order to solve this problem, infrared image background suppression is a key preprocessing technology, which can effectively suppress The complex undulating background enhances the contrast between the target and the background, which is conducive to improving...
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): G06T5/50
CPCG06T5/50G06T2207/10048G06T2207/20221G06T7/11
Inventor 秦翰林王婉婷程文雄延翔王春妹梁瑛杨硕闻彭昕胡壮壮
Owner XIDIAN UNIV