Unlock instant, AI-driven research and patent intelligence for your innovation.
A method for automatic identification of Chinese yew in high-resolution remote sensing images
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A remote sensing image, high-resolution technology, used in character and pattern recognition, instrumentation, computing, etc., can solve problems such as high cost, difficulty in supervised classification algorithms, and low efficiency.
Active Publication Date: 2018-11-06
CHANGCHUN INST OF TECH
View PDF2 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0003] In the current application and research, there are two ways to find the Northeast yew in an area: one is to find the tree species through field investigation. Since the Northeast yew is distributed in mountainous areas with an altitude of 500-1000 meters, such areas are vast and most It is difficult to reach, the cost is high and the efficiency is low through on-the-spot investigation; the second is to use the supervised classification algorithm to identify the Northeast yew in high-resolution remote sensing images, and the content of remote sensing images captured by satellites can cover a large area. On the basis of learning a large number of ground target samples, supervised classification algorithms such as Convolutional Neural Networks can identify targets in remote sensing images quickly and at low cost. It is difficult to obtain a sufficient number of ground samples of Northeastern yew to train the algorithm. On the other hand, since most recognition algorithms have the characteristics of tolerable scale or color changes, it is difficult to distinguish the Northeastern yew from other mixed plants, resulting in supervision. Classification Algorithms Difficult to Work
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0087] Taking a high-resolution remote sensing image of the Laoyeling area as an example, the size of the image is 2000*2000 and the resolution is 1 meter. By using the method described in this patent, it is compared with the traditional neural network, support vector machine, and random forest methods , the accuracy comparison of yew recognition is as follows (see Figure 1 to Figure 5 ):
[0088] S1, input the high-resolution remote sensing image image of the Laoyeling area, calculate the scale Size of the image block to be analyzed, and select a coordinate position (H HD , L HD ), the coordinate position of a non-coniferous vegetation (H FZY , L FZY ), a non-northeast yew coniferous plant coordinate position (H FHD , L FHD ):
[0089] where H HD =384,L HD =187
[0090] where H FZY =1064,L HD =571
[0091] where H FHD =426,L FHD =151
[0092] Size=450
[0093] S2, for all pixels in the image, calculate its vegetation feature value (Vfeature) according to the ...
Embodiment 2
[0101] Taking a high-resolution remote sensing image of Zhang Guangcai Mountain as an example, the size of the image is 5000*5000 and the resolution is 0.5 meters (see Figure 1 to Figure 5 );
[0102] S1, input the high-resolution remote sensing image image of Zhang Guangcai Mountain, calculate the scale Size of the image block to be analyzed, and select a coordinate position (H HD , L HD ), the coordinate position of a non-coniferous vegetation (H FZY , L FZY ), a non-northeast yew coniferous plant coordinate position (H FHD , L FHD ):
[0103] where H HD =384,L HD =187;
[0104] where H FZY =1064,L HD = 571;
[0105] where H FHD =426,L FHD = 151;
[0106] Size=900;
[0107] S2, for all pixels in the image, calculate its vegetation feature value (Vfeature) according to the scale Size of the image block to be analyzed:
[0108] S3, according to the vegetation eigenvalues of all pixels in the Image, the location of Taxus chinensis (H HD , L HD ), the locati...
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 present invention provides a method for identifying Taxus chinensis in high-resolution remote sensing images, which requires only a small amount of ground samples to achieve high-precision identification of Taxus chinensis in high-resolution remote sensing images, making full use of the low-cost coverage area of remote sensing images The biggest advantage is that the Northeast Taxus can be identified from remote sensing images based on the unique characteristics of the Northeast Taxus based on fewer samples, and better recognition quality can be obtained, which has high social and economic values.
Description
technical field [0001] The invention belongs to the technical field of remote sensing image analysis and processing, and in particular relates to a method for automatically identifying Northeast yew in high-resolution remote sensing images. Background technique [0002] Northeast yew is a species of endangered plants under national first-class protection. It is a precious tree species left over from the tertiary period. It has a history of 2.5 million years and has high research value; a variety of anti-cancer substances can be extracted from the Northeast yew, which is the most promising anti-cancer drug in the world. one of the cancer drugs. Most of these tree species are distributed in Laoyeling, Zhangguangcailing and Changbai Mountains in Jilin Province. Locating and identifying the location of these trees will help protect and make full use of this unique species, which has high ecological, social and economic values. [0003] In the current application and research, ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More