A Cloud Detection Method of Panchromatic Band Remote Sensing Image Based on Gaussian Fitting Function and Fuzzy Mixture Estimation
A Gaussian fitting, remote sensing image technology, applied in computing, image analysis, image enhancement and other directions, to achieve the effect of less misjudgment, fast calculation speed and high detection accuracy
Active Publication Date: 2020-12-29
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS +1
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide a panchromatic band remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation, which can overcome the above-mentioned deficiencies in the existing cloud detection method technology, and meet the requirements of high-efficiency on single panchromatic band image data. Automated Cloud Zone Detection Requirements
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
[0023] The specific implementation method of the embodiment includes the following steps:
[0024] Step 1, adaptive initial binary labeling: use the Otsu algorithm to calculate the adaptive binary segmentation threshold of the panchromatic band remote sensing image, and divide the image into a high-brightness data set and a low-dark data set according to the grayscale according to the binary segmentation .
[0025] In the embodiment, without any prior knowledge, such as cloud images and other data assistance, for a panchromatic satellite remote sensing image, the Otsu algorithm is used to binarize the image, and the pixel positions on the image are determined according to the grayscale feature Divided into two categories and labeled, one is a high-brightness dataset and the other is a low-dark dataset.
[0026] Step 2, fuzzy estimation of Gaussian fitting function: According to the statistical results of the histogram on the two types of data sets, use the Gaussian fitting fu...
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 provides a panchromatic wave band remote sensing image cloud detection method based on a Gaussian fitting function and fuzzy mixed estimation. The method comprises the steps that after self-adaptive binary judgment of an image is conducted, initial marking on two kinds of pixel data with the bright gray scale and the dark gray scale is achieved; new Gaussian fitting function parameters are calculated through a fuzzy estimation method in the two kinds of marked pixels, gray scale binary segmentation threshold value estimation is conducted, two kinds of binary segmentation threshold values are calculated in a weighed mode to obtain an iterative binary mark of the overall image, fuzzy estimation of the Gaussian fitting function is conducted again on the iterative mark, the binary segmentation threshold values of the two kinds of data sets are gradually converged to be similar and then meet a threshold value tolerance, a final high-brightness image spot gray scale segmentation threshold value is obtained, and panchromatic wave band remote sensing image cloud detection is achieved. The method has the advantages that two kinds of high-brightness image spot gray scales with the long distance are continuously converged to be consistent through self-adaptive segmentation and classification of panchromatic wave band image gray scales by combining the Gaussian fitting function with the fuzzy mixed estimation method, therefore, a cloud detection threshold value which is accurately estimated is calculated, and the detection precision, breadth and depth are significantly improved.
Description
technical field [0001] The invention belongs to the field of surveying and mapping science and technology, and relates to a panchromatic band remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation, which is mainly used in the fields of optical satellite remote sensing data processing and application. Background technique [0002] For a long time, land resource optical satellite images have been limited by the influence of clouds, and there is a bottleneck in large-scale earth observation. The existence of cloud areas not only covers ground object information, but also causes many effects on image registration, fusion and other processing. At present, the commonly used cloud detection algorithms mainly include texture analysis method, homomorphic filtering method, multi-spectral synthesis method and so on. Texture analysis extracts the spatial characteristics of cloud and non-cloud areas based on statistical methods, which c...
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): G06T7/11G06T7/136G06T5/30G06T5/40
CPCG06T2207/10032
Inventor 王博凌霄康一飞胡旭东卢毅吴菲菲
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS