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

Crop recognition method based on multi-spectral satellite images

A technology of satellite imagery and recognition method, which is applied in the field of multi-spectral information processing, can solve the problems of high cost and low efficiency of crop recognition technology, and achieve the effect of expanding the number, accurate recognition and improving recognition efficiency

Active Publication Date: 2018-12-21
成都天地量子科技有限公司
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a crop recognition method based on multi-spectral satellite imagery for the problems of low efficiency and high cost of the existing crop recognition technology, and to train a machine learning model by introducing time-series spectral information of crops, thereby improving crop recognition. Efficiency, while reducing application costs by using multi-spectral satellite image data, so that the present invention can be applied to a wide range of crop identification

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 recognition method based on multi-spectral satellite images
  • Crop recognition method based on multi-spectral satellite images
  • Crop recognition method based on multi-spectral satellite images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] A method for crop identification based on multi-spectral satellite images provided by a preferred embodiment of the present invention, such as figure 1 shown, including the following steps:

[0040] S1, collecting crop samples;

[0041] Collect crop samples, and record the collection time, location and type of crops; for a range of 100km×100km, the number of samples for each crop should be at least 100, and should be scattered as much as possible;

[0042] S2. Acquiring multi-spectral satellite image data of the crop samples;

[0043] The multispectral satellite image data is the number of multispectral satellite images from the collection time of crop samples to the 60 days before the collection time; the longer the time period, the more multispectral satellite images are obtained, and more spectral Information is more helpful to improve the accuracy of crop classification. Therefore, in order to ensure the accuracy of crop classification, this embodiment preferably ...

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 identification method based on multi-spectral satellite images, comprising the following steps: S1, collecting crop samples; S2, acquiring multispectral satellite imagedata of the crop sample; S3, determining a pixel corresponding to the crop sample on the multi-spectral satellite image data through the collection position of the crop sample; S4, taking the temporalspectrum information of the pixel and the crop type of the crop sample as inputs to train a machine learning model; S5, classifying other sampling areas by the trained machine learning model. The invention takes the temporal spectrum information of the pixel as the input of the training machine learning model, Not only greatly expands the amount of crop spectral information, solves the problem ofinsufficient crop spectral information at a single time, but also identifies crops from the full cycle of crop growth spectral information, which is more accurate than the identification at a singletime, so as to improve the efficiency of crop identification.

Description

technical field [0001] The invention belongs to the technical field of multispectral information processing, in particular to a crop identification method based on multispectral satellite images. Background technique [0002] Agriculture is the foundation of the national economy, and crops, as the foundation of agriculture, play a pivotal role in ensuring food security and social stability. Accurate and rapid grasp of crop planting area and its spatial distribution is crucial to ensuring food security. [0003] The existing regional crop species identification and planting area statistics are mainly obtained through extensive ground survey and sampling, and then combined with statistical principles to analyze the sample data. This research method requires a lot of manpower and material resources, and at the same time takes a long time, and cannot be updated frequently in a large area (such as the whole country). [0004] Another crop identification method is mainly the remo...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/13G06F18/24G06F18/214
Inventor 刘云杰钱佳君李雷夏深圳叶昕周公器吕童王驰
Owner 成都天地量子科技有限公司
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