A method and system for large-scale remote sensing classification of crops
A classification method, crop technology, applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve data hunger and other problems, achieve the effect of reducing workload, improving classification accuracy and efficiency, and improving classification accuracy
Active Publication Date: 2019-01-04
BEIJING NORMAL UNIVERSITY
View PDF4 Cites 7 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 large-scale crop remote sensing classification method and system to improve the classification accuracy and efficiency of large-scale remote sensing image classification, and to solve the "data hunger" problem in the traditional large-scale remote sensing classification method
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
[0060] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts all belong to the protection scope of the present invention.
[0061] The purpose of the present invention is to provide a large-scale remote sensing classification method and system for crops, to improve the classification accuracy and efficiency of large-scale remote sensing image classification, and to solve the "data hunger" problem in traditional large-scale remote sensing classification methods.
[0062] In order to make the above objects, features and advantages of the present invention more compreh...
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 discloses a large-scale crop remote sensing classification method and system. The method and the system establish a migration remote sensing network RSNet model according to a residual network model and a pyramid pooling network model, and pre-train the migration RSNet model according to a historical training sample in a large range of crop labeling samples in a historical year, a pre-training migration RSNet model is established, wherein the migration RSNet model comprises a residual network model and a pyramid pooling network model. The pre-training model is fine-tuned based onthe random and independent distribution of high-precision crop marker samples in the small area of the current potential, and then the large-scale crop classification is realized based on the fine-tuning model. The present invention provides a fine-tuning model of crop labeling samples in a small area, which greatly improves the classification accuracy of large-scale crops as a whole, the methodrealizes the migration of the spatial scale of the crop labeling samples, solves the problem that the labeling samples in the traditional crop classification are limited to the specific region, the specific image and the specific target, and improves the classification accuracy and the classification efficiency of the large-scale crop.
Description
technical field [0001] The invention relates to the technical field of crop classification, in particular to a large-scale remote sensing classification method and system for crops. Background technique [0002] Efficient and accurate classification of large-scale remote sensing images is a long-term scientific problem in remote sensing. The remote sensing classification of crops and their spatial distribution monitoring is the main entry point of agricultural research, and it is also one of the key issues in the promotion process of agricultural remote sensing. With the development of remote sensing data sources and remote sensing technology, traditional large-scale crop remote sensing classification methods for remote sensing images have made great progress in terms of classification accuracy and efficiency. According to different data sources, traditional large-scale remote sensing classification methods for large-scale crops can be divided into classification based on s...
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): G06K9/00G06K9/62
CPCG06V20/188G06F18/24G06F18/214
Inventor 张锦水刘红利潘耀忠杨珺雯许晴
Owner BEIJING NORMAL UNIVERSITY