Hyperspectral Image Classification Method Based on Binary Quantization Network
A hyperspectral image, binary quantization technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of high method complexity, blurred image edges, low classification accuracy, etc. The network structure is complex, the storage space is solved, and the effect of reducing the number of multiplication operations
Active Publication Date: 2022-03-04
XIDIAN UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of the present invention is to address the deficiencies in the prior art above, and propose a hyperspectral image classification method based on a binary quantization network, which is used to solve the image edge blurring that exists when the existing hyperspectral image classification method is used for cloud classification , the technical problems of high method complexity, large amount of computation and low classification accuracy
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
[0047] The present invention will be further described below in conjunction with the accompanying drawings.
[0048] Refer to attached figure 1 , to further describe the specific steps of the present invention.
[0049] Step 1. Generate a training set.
[0050] Cut N hyperspectral images with a size of W×H×C containing clouds into M hyperspectral images with a size of 512×512×N, where 60<N<120, W, H and C represent hyperspectral images respectively Width, height and number of bands, 1000<W<2000, 1000<H<2000, 3<C<256, the unit of W, H and C is pixel, 8000<M<16000.
[0051] Using the cloud proportion formula, calculate the cloud proportion of each cropped image, judge the cropped hyperspectral image with cloud proportion less than 10% as cloudless image, and judge the rest as cloudy image.
[0052] The cloud ratio formula is as follows:
[0053]
[0054] Among them, ε i Indicates the cloud proportion of the i-th image after cropping, p i Indicates the total number of cl...
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 proposes a hyperspectral image classification method based on a binary quantization network, which mainly solves the technical problems of fuzzy edges of hyperspectral images, complex models, and insufficient spatial feature information of extracted clouds. The implementation steps are: generate a training set; construct a full-precision convolutional neural network; train a full-precision convolutional neural network; construct a binary quantized convolutional neural network; initialize a binary quantized convolutional neural network; train a binary quantized convolutional neural network Network; Classifying hyperspectral images. The present invention utilizes seven quantization modules, simplifies the traditional convolutional neural network structure, fully extracts the spatial feature information of hyperspectral image clouds, and improves the accuracy of hyperspectral image cloud classification while saving computing resources.
Description
technical field [0001] The invention belongs to the technical field of image processing, and further relates to a hyperspectral image classification method based on a binary quantization network in the technical field of image classification. The invention can be used to classify cloudy images and cloudless images from hyperspectral images. Background technique [0002] Hyperspectral imagers can image objects in hundreds of narrow bands, ranging from visible light to infrared bands, and the feature of "integration of images and spectra" enables them to obtain more information. At present, hyperspectral data processing has become an important research field at home and abroad. Among them, hyperspectral image cloud classification has important theoretical value and application prospects in aviation flight support and weather forecasting. According to the proportion of clouds, hyperspectral images can be divided into two categories: less cloudy and more cloudy. However, hype...
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): G06V10/764G06V10/774G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06V20/194G06V20/13G06N3/045G06F18/24G06F18/214
Inventor 雷杰苏展吴凌云李云松谢卫莹张鑫
Owner XIDIAN UNIV