Forestry harmful organism intelligent identification system on basis of multi-source image information

Abstract

The invention provides a forestry harmful organism intelligent identification system on the basis of multi-source image information. The system comprises an unmanned aerial vehicle and a ground station; the unmanned aerial vehicle is equipped with a temperature and humidity module, a communication module and a control module and further equipped with a GPS positioning module, a sensing module and an image capture module which are connected with the control module, and the temperature and humidity module is connected with the control module; the communication module achieves communication of the control module of the unmanned aerial vehicle and the ground station; and forestry harmful organism information is extracted through a satellite remote sensing image, an unmanned aerial vehicle remote sensing image and an image identification technology, and an image collected by an image collection module is subjected to image automatic identification through spectral information and time phase information in time sequence image data to obtain the harmful organism occurrence condition. Compared with satellite remote sensing and airborne and spaceborne remote sensing, the forestry harmful organism intelligent identification system on the basis of the multi-source image information is low in cost, high in accuracy and easy to control.

Description

technical field [0001] The invention relates to the technical fields of UAV remote sensing, satellite remote sensing, spatial data analysis and processing, image processing and forestry; in particular, it relates to an intelligent pest identification system based on multi-temporal satellite images, UAV remote sensing images, and image recognition technology. Background technique [0002] The traditional investigation of forestry diseases and insect pests mainly relies on manual visual inspection, forest sampling and other methods. Although these methods have high authenticity and reliability, they are time-consuming, labor-intensive, and have disadvantages such as representativeness, poor timeliness, and strong subjectivity. They are difficult to meet the current needs of large-scale monitoring and forecasting of pests and diseases. [0003] Remote sensing technology is currently the only means that can quickly obtain spatially continuous land surface information in a large ...

AI Technical Summary

Problems solved by technology

At present, there is no method to use multi-temporal satellite image data to monitor forestry diseases on a regional scale in a large scale, and then use dr...

Images