Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Crop intelligent remote sensing extraction method and system based on transfer learning

A transfer learning and extraction method technology, applied in the field of intelligent remote sensing extraction of crops based on transfer learning, to achieve the effect of reducing data dependence, improving classification accuracy, and controlling differences in phenological characteristics

Pending Publication Date: 2022-03-11
HUAZHONG NORMAL UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although machine learning has become the mainstream technology for solving perceptual problems, it is still difficult to use a general learning model compatible with different data and different tasks

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
  • Crop intelligent remote sensing extraction method and system based on transfer learning
  • Crop intelligent remote sensing extraction method and system based on transfer learning
  • Crop intelligent remote sensing extraction method and system based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The embodiment of the present invention provides a method and system for intelligent remote sensing extraction of crops based on migration learning, which can accurately identify target crops at a regional scale without relying on a large number of training samples, with high efficiency, good robustness, and high classification accuracy.

[0034] see figure 1 , the technical solutions in the embodiments of the present invention are to achieve the above-mentioned technical effects, the general idea is as follows:

[0035] The first step is to construct a feature data set: according to the conditions of the research area and the characteristics of the target crops, obtain the characteristic images that can best distinguish the target crops, including the spectral features, texture features, and shape features of the target. These features will be Provide a basis for the classification of target crops. Taking winter rape as an example, relevant studies have shown that the...

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

No PUM Login to View More

Abstract

The invention discloses a crop intelligent remote sensing extraction method and system based on transfer learning. Based on geospatial autocorrelation, a partition transfer learning strategy is adopted, a target image is partitioned in a geographic subarea mode, it is ensured that a training sample of a machine learning model of an image of each geographic subarea comes from a classification result of an adjacent image, classification learning is carried out in a small range, and the classification result of the machine learning model of the image of each geographic subarea is obtained. Classification learning results are gradually extrapolated to adjacent sub-regions, crops in a research region are extracted from the local part to the whole part, phenological characteristic differences, caused by regional differences, of the same kind of crops can be effectively controlled, and classification precision is improved.

Description

technical field [0001] The invention relates to the technical field of smart agriculture, in particular to a method and system for intelligent remote sensing extraction of crops based on transfer learning. Background technique [0002] Agriculture is the foundation of human survival and development, and also the fundamental condition for national economic development and social stability. Timely, accurate and efficient access to crop planting area and temporal and spatial distribution information is of great practical significance for optimizing crop planting structure, maintaining national food security and promoting sustainable human development. Traditional agricultural monitoring methods mainly include statistical report methods and sampling survey methods, which cannot guarantee the timeliness of large-scale crop planting information acquisition, and are easily affected by human subjective factors. [0003] In the field of remote sensing mapping of crops, the more comm...

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
no application Login to View More
IPC IPC(8): G06V20/10G06V10/764G06K9/62
CPCG06F18/24
Inventor 陶建斌吴琪凡王昀张馨月
Owner HUAZHONG NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com