Unlock instant, AI-driven research and patent intelligence for your innovation.

Infrared image volume cloud detection method based on boundary fractal dimensions

An infrared image, fractal dimension technology, applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of cirrus detection, artificial extraction of feature uncertainty, inability to use machine learning, etc., to avoid uncertainty , improve the detection accuracy and recall rate, the effect of simple calculation

Inactive Publication Date: 2019-04-19
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is: the present invention provides a kind of infrared image cirrus cloud detection method based on boundary fractal dimension, proposes the new train of thought that utilizes cirrus cloud edge to have larger fractal dimension characteristic to detect cirrus cloud, solves existing small sample situation Unable to use machine learning to detect cirrus clouds and manually extract feature uncertainty

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 volume cloud detection method based on boundary fractal dimensions
  • Infrared image volume cloud detection method based on boundary fractal dimensions
  • Infrared image volume cloud detection method based on boundary fractal dimensions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0080] Step 1: Input the infrared image to be processed, such as figure 2 As shown, perform morphological reconstruction on the infrared image to be processed;

[0081] Step 2: Carry out K-means clustering on the reconstructed image based on step 1, such as image 3 shown;

[0082] Step 3: Set the size of the image block to 50x50, divide the infrared image obtained in step 2 into blocks and extract the edge of the image block, some image blocks are as follows Figure 4 shown;

[0083] Step 4: Calculate the fractal dimension of the edge of each image block, such as Figure 5 shown;

[0084] Step 5: Screen the fractal dimension of the edge of the image block according to the set threshold 1.759 to obtain the detection result, such as Figure 6 shown.

[0085] Among them, the morphological reconstruction steps:

[0086] Gaussian low-pass filtering is performed on the infrared image to obtain a denoising infrared image;

[0087] The denoising infrared image is continuousl...

Embodiment 2

[0101] Based on Example 1, the details of passing the edge and calculating its fractal dimension are as follows:

[0102] Use the Canny algorithm to extract the edge of the image block:

[0103] Smooth image blocks using a Gaussian filter;

[0104] Calculate the gradient magnitude and angle of the smoothed image block;

[0105] Apply non-maximum suppression to the gradient magnitude, and use the set double thresholding and connecting edges to obtain image patch edges, where double thresholding: low threshold is 0.031, high threshold is 0.078. Since the Canny algorithm is an existing algorithm, the specific operation steps are as above, and other details are not repeated here;

[0106] Compute the fractal dimension of the image patch edges using the box count dimension method:

[0107] Use the box count dimension method, which is defined as follows:

[0108] Suppose A is R n Any non-empty bounded subset in space, for any size r > 0, N(r) represents the minimum number of n-...

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 volume cloud detection method based on boundary fractal dimension, and relates to the field of target and false alarm source detection in infrared image processing. The method comprises the steps of 1, after inputting a to-be-processed infrared image, performing morphological reconstruction on the to-be-processed infrared image to obtain a reconstructed image; Step 2, performing K-means clustering on the reconstructed image to obtain an image with a background area removed and an area where cloud is located; Step 3, partitioning the image obtained in the step 2 to obtain image blocks; 4, extracting image block edges, and calculating fractal dimensions of the image block edges; 5, screening fractal dimensions of the edges of the image blocks according to a set threshold value, obtaining the image blocks where the volume clouds are located, and completing detection; According to the method, the inherent characteristic of larger fractal dimensionof the edge of the volume cloud is utilized, the image edge is extracted, the fractal dimension of the edge is calculated for detection, a brand-new volume cloud detection method which is rapid in calculation and high in efficiency is provided, and the uncertainty of manual feature extraction in an existing method is avoided.

Description

technical field [0001] The invention relates to the field of target and false alarm source detection in infrared image processing, in particular to an infrared image cirrus cloud detection method based on boundary fractal dimension. Background technique [0002] Infrared images are widely used in the military, such as security monitoring, target tracking, etc. Therefore, the extraction of different types of targets in infrared images has become a research hotspot in recent years. There are often interference detection scenes in infrared weak target detection, and cirrus clouds are one of them, so extracting cirrus clouds in infrared images can effectively reduce interference. At present, there are few detection methods for cirrus clouds in infrared images, and because of the long imaging distance and low resolution of infrared images, cirrus clouds in infrared images are easily confused with other interference information such as the background, making detection more difficu...

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): G06T7/13G06T7/136G06T5/00G06K9/62
CPCG06T7/13G06T7/136G06T2207/30192G06T2207/20021G06T2207/10048G06F18/23213G06T5/70
Inventor 刘雨菡吕昱霄张鹏飞宋立彭真明曹思颖王光慧曹兆洋蒲恬赵学功杨春平
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA