Real-time identification system and method for crops based on unmanned aerial vehicle

Abstract

The invention discloses a real-time identification system for crops based on an unmanned aerial vehicle. The system comprises an unmanned aerial vehicle platform, a route planning module, a crop identification module, a server and a mobile terminal, wherein the unmanned aerial vehicle platform is provided with an image acquisition device and the crop identification module, and the route planning module is arranged in the server. The invention further discloses a real-time identification method for crops based on the unmanned aerial vehicle. According to the method, after the server plans the route of the unmanned aerial vehicle, the route is uploaded to the mobile terminal, and the unmanned aerial vehicle can execute crop image collection and real-time crop identification tasks after receiving an instruction, and upload the obtained crop image and a final identification result to an agricultural condition database. The crop identification module is realized based on a crop identification model trained by YOLOv3.

Description

Technical field [0001] The present invention relates to crop survey, monitoring technology, and more particularly, to a UAV based on real-time identification of the system and method of crops. Background technique [0002] Throughout ancient and modern, is the agriculture of our country was founded on, play a vital role in my country's economic development. In recent years, domestic and foreign scholars in the use of remote sensing technology to identify the type of crops of some progress, and most of the time sequence of remote sensing and crop phenological characteristics combine to achieve crop classification. Driven by the rapid development of my country's agricultural modernization, "precision agriculture" concept has penetrated into all aspects of agricultural production. UAV its operational flexibility, high resolution advantages, has become an important tool for gathering information on precision agriculture, particularly crops are widely used classification, the nature o...

AI Technical Summary

Problems solved by technology

[0004]2. Uncertainty of remote sensing data: remote sensing data is easily interfered by external factors such as weather, atmosphere, electromagnetic, etc., and the resolution is low, which leads to the uncertainty of remote sensing image classification High uncertainty of results and low accuracy of crop type identification

[0005]3. The field operation environment is complex: In the actual agricultural situation survey, there are scattered rural buildings, intricate wires, trees of different heights, and river networks in the operation of drones. Density, uneven distribution of field size, etc.

[0006]4. The storage of crop types is complicated: currently in the survey of agricultural conditions, although drones have been used to obtain near-ground drone image data, but Inconvenient communication and coordination between internal and external industries often occur

Moreover, the type of crops and warehousing work in the later period are mostly manual. If there is a lack of quantity or quality in the survey samples, it cannot be made up, which will greatly reduce the work efficiency and the accuracy of the survey work.

Images