High resolution panchromatic remote sensing image cloud discriminating method
A remote sensing image and high-resolution technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of inability to achieve de-correlation compression effects, etc., to improve the accuracy and real-time performance of cloud judgment, ensure accuracy, The effect of high probability of detection
Inactive Publication Date: 2013-05-08
HARBIN INST OF TECH (BEIJING) IND TECH INNOVATION RES INST CO LTD
View PDF1 Cites 13 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The traditional feature compression method is linear discriminant analysis (LDA). This method is suitable for the classification of two types of samples with the same covariance. For two types of samples with different covariance, it cannot achieve the best decorrelation compression effect.
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
[0029] In order to make the purpose, method and advantages of the present invention clearer, the technical solutions of the present invention will be further described below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited.
[0030] The present invention first performs fast SVD decomposition on the scanned image block, and calculates the first three singular values as input feature vectors. Then, using the feature compression algorithm based on heteroscedastic discriminant analysis (HDA) technology, the feature space is compressed into one-dimensional subspace, and the optimal threshold is found as a classifier in the one-dimensional compressed subspace based on the principle of minimizing the false alarm rate. Finally, the trained classifier is used to perform cloud detection on the input image. Specific steps are as follows:
[0031] 1. Select 500 training samples of clouds and ground objects, which are record...
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 high resolution panchromatic remote sensing image cloud discriminating method and relates to the technical filed of space photoelectricity information processing. In order to solve panchromatic remote sensing image cloud detecting problem, enable a detecting result to be more accuracy and achieve real-time requirements, the high resolution panchromatic remote sensing image cloud discriminating method comprises the following steps that (1) a training image is conducted by a normalization processing, (2) singular value decomposition is conducted to the extracted normalization processing image and singular values can be extracted as characteristic parameters, (3) utilizing the method, a training sample is mapped as points in a characteristic space, (4) feature extraction is conducted to the characteristic space by utilizing a high definition audio (HDA) method, (5) a signal threshold value is structured as cloud detection criteria in an obtained one-dimensional compressed subspace, (6) cloud detection is conducted to a to-be-trained image by utilizing a trained classifier. The high resolution panchromatic remote sensing image cloud discriminating method has the advantages of being suitable for the cloud detection of the high resolution panchromatic remote sensing image. The high resolution panchromatic remote sensing image cloud discriminating method has high detection probability and low false alarm probability and occupies little storage space and operation time consuming of a processing system.
Description
technical field [0001] The invention relates to the technical field of space photoelectric information processing, in particular to a remote sensing image cloud judgment technology based on pattern recognition for a high-resolution panchromatic optical satellite imaging platform. Background technique [0002] With the development of space technology, higher requirements are put forward for space remote sensing, mainly including high spatial resolution, high spectral resolution and high temporal resolution. What followed was that the data volume of space remote sensing images increased geometrically, and the requirements for data transmission code rates increased to hundreds or even thousands of Mbps, but the current maximum transmission rate is only 300-600 Mbps, which has become a constraint for space remote sensing images. The "bottleneck" of resolution improvement. In fact, remote sensing images covered by clouds (such as Figure 1-3 shown) accounted for more than 50% of...
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 Applications(China)
IPC IPC(8): G06K9/62
Inventor 赵晓侯晴宇张伟梁冰冰陈刚义丛海佳孙永雪
Owner HARBIN INST OF TECH (BEIJING) IND TECH INNOVATION RES INST CO LTD