Agricultural and forestry crop identification method based on medium-high resolution time sequence remote sensing data

A high-resolution, remote sensing data technology, applied in the field of remote sensing applications, can solve the problems of insufficient information utilization, low accuracy of crop category recognition, and low degree of interpretation automation
CN109960972AActive Publication Date: 2019-07-02BEIJING AEROSPACE TITAN TECH CO LTD

Patent Information

Authority / Receiving Office
CN ยท China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING AEROSPACE TITAN TECH CO LTD
Publication Date
2019-07-02

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an agricultural and forestry crop identification method based on medium-high resolution time sequence remote sensing data. The method comprises the steps of 1) carrying out thecross calibration on remote sensing images observed by multiple medium-high resolution remote sensors in the same region at different times; 2) for remote sensing images with different spatial resolutions, forming a remote sensing time sequence data set with consistent spatial resolutions and short time intervals on the basis of cross calibration; 3) segmenting the agriculture and forestry land parcels in the remote sensing image by using an image segmentation method to obtain the boundary of each land parcel; 4) analyzing the remote sensing time sequence data set by taking the land parcels as units, and counting the average value and variance of the spectral band reflectivity, the normalized vegetation index and the leaf area index of the land parcels in each period; sorting the statistical characteristics according to time to form a plurality of characteristic curves of the plot; and 5) matching the plurality of characteristic curves of the agriculture and forestry land parcels withthe phenological characteristic library to obtain the crop types of the land parcels.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of remote sensing applications, in particular to the application of medium and high-resolution time-series remote sensing data in identifying agricultural and forestry crops, and in particular to a method for identifying agricultural and forestry crops based on medium- and high-resolution time-series remote sensing data. Background technique

[0002] The identification of agricultural and forestry crops is the basis of remote sensing monitoring of agricultural and forestry crops such as growth monitoring and crop yield estimation. There are three main methods for remote sensing identification of agricultural and forestry crops:

[0003] 1. Manual visual interpretation. Professionals obtain specific target object information on remote sensing images through direct observation or with the help of auxiliary interpretation instruments. This method is limited by the technical level of personnel and is labor-intensive and...

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