A cross-domain ground-based cloud image classification method based on migration visual information
A ground-based cloud image and visual information technology, which is applied in the field of cross-domain ground-based cloud image classification based on migration of visual information, can solve problems such as the decline in classification accuracy, and achieve the effect of improving the accuracy rate
Active Publication Date: 2020-07-17
TIANJIN NORMAL UNIVERSITY
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although the above ground-based cloud image classification methods can achieve good classification results when training and testing in the same domain, when training in the source domain and testing in the target domain, the classification accuracy of these methods will decline to varying degrees
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
[0055] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in combination with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are exemplary only, and are not intended to limit the scope of the present invention. Also, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concept of the present invention.
[0056] figure 1 It is a flow chart of a cross-domain ground-based cloud image classification method based on migration visual information proposed according to an embodiment of the present invention. The following uses figure 1 Some specific implementation processes of the present invention are described by way of example. The method of the present invention is a cross-domain ground-based cloud image classification meth...
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 embodiment of the present invention discloses a cross-domain ground-based cloud image classification method based on migration visual information. The method includes: preprocessing multiple input ground-based cloud images from the source domain and the target domain to obtain a training ground-based cloud image; dividing the training ground-based cloud image into Multiple image blocks, and densely extract features in each image block to obtain the feature vector set of the image block; maximize the extraction of all feature vectors to obtain the migration feature vector of the training base cloud map; perform weighted metric learning based on the migration feature vector, Obtain the distance function, and use the distance function on the nearest neighbor classifier to obtain the ground-based cloud image classifier; obtain the migration feature vector of the test ground-based cloud image from the source domain and the target domain, and input it to the ground-based cloud image classifier to obtain the ground-based cloud image category recognition result. The invention can effectively excavate salient feature information, fully consider the sample pairs from the source domain and the target domain and the number of sample pairs of each category, and improve the accuracy rate of cross-domain ground-based cloud image classification.
Description
technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to a cross-domain ground-based cloud map classification method based on migration visual information. Background technique [0002] Clouds are visible aggregates formed by small water droplets, ice crystal particles, or a mixture of the two suspended in the atmosphere, and are an important and common weather phenomenon. Under normal circumstances, clouds cover about 50% of the earth's surface, and they are the main regulator of the radiation budget of the earth-atmosphere system (the ground and the atmosphere are regarded as a whole, called the earth-atmosphere system), and they affect the radiation balance and heat balance of the earth-atmosphere system. It is an important factor affecting the Earth's climate system. [0003] Ground-based cloud image classification technology is the basis for building an automatic ground-based cloud image classification sys...
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): G06K9/62G06K9/46
CPCG06V10/40G06V10/467G06F18/24147
Inventor 张重李东红刘爽穆嘉松
Owner TIANJIN NORMAL UNIVERSITY