Vegetable field monitoring method based on multi-source multi-temporal remote sensing image data

Abstract

The present invention belongs to the technical field of remote sensing application, and discloses a vegetable field monitoring method based on multi-source multi-temporal remote sensing image data. The method comprises the steps of: determining a type and a phenological phase of a vegetable field and an interfering ground object, and selecting optimal phases of vegetable field and interfering ground object identification; acquiring multi-source multi-temporal remote sensing image data and service specific vector data; and by using an object-oriented classification method and combining parcel-level cultivated land vector data, performing vegetable field data extraction, and extracting vegetable data according to the two optimal phases and taking an intersection, so as to obtain a vegetable field monitoring result. According to the method, vegetable field monitoring is performed based on multi-source multi-temporal remote sensing image data, so that influence of interfering ground object is effectively reduced, and monitoring precision is improved.

Description

technical field [0001] The invention belongs to the technical field of remote sensing applications, and relates to a vegetable field monitoring method based on multi-source and multi-temporal remote sensing image data. Background technique [0002] Timely and accurate monitoring of vegetable field planting area is of great significance for the rational development of vegetable industry. In terms of remote sensing monitoring of crops, there are many researches on remote sensing monitoring of large field crops such as wheat, rice, and corn, but less research on remote sensing monitoring of vegetable fields. In the past, the remote sensing data source of crop remote sensing monitoring was single, and the monitoring area could not be effectively covered in a short period of time. In addition, human-computer interaction interpretation methods or support vector machine (SVM) automatic classification technology were often used to extract vegetable field information, but the efficie...

AI Technical Summary

Problems solved by technology

In the past, remote sensing monitoring research on crops has a single source of remote sensing data, which cannot effectively cover the monitoring area in a short period of time. In addition, human-computer interaction interpretation methods or support vector machine (SVM) automatic classification technology are often used to extract vegetable field information, but the efficiency is low. Interfering ground objects have a great influence and the classification accuracy is limited

Images