Jetson TK1 based rice weed unmanned aerial vehicle monitoring system and monitoring method thereof

Abstract

The invention discloses a Jetson TK1 based rice weed unmanned aerial vehicle monitoring system and a monitoring method thereof. The system comprises an unmanned aerial vehicle and a ground control station, wherein the unmanned aerial vehicle is provided with a Jetson TK1 based flight control module, a wireless transparent transmission module and an image collection module, the first wireless transparent transmission module and the image collection module are electrically connected with the flight control module respectively, the image collection module comprises a GOPRO camera and an image collection card, the ground control station comprises a PC terminal ground station and a second wireless transparent transmission module, the second wireless transparent transmission module is electrically connected with the PC terminal ground station, and the ground control station is in wireless communication connection with the flight control module through the first wireless transparent transmission module and the second wireless transparent transmission module. The Jetson TK1 based rice weed unmanned aerial vehicle monitoring system disclosed by the invention can analyze a collected real-time image in real time, thus improving the working efficiency, and the distribution and severity level of the weeds are displayed on an offline map of the ground control station, thereby being intuitiveand convenient.

Description

technical field [0001] The invention relates to the technical field of rice weed image recognition, in particular to a Jetson TK1-based drone monitoring system for rice weeds and a monitoring method thereof. Background technique [0002] Rice weeds cause serious harm to the growth of rice. Weeds will absorb nutrients, water, etc. around the rice, and will affect the sunlight and air of nearby rice, directly affecting the growth of rice. The more weeds, the better the growth of rice. weaker. In order to solve the problem of precise weeding by realizing the variable spraying of herbicides, the application of UAVs to collect remote sensing images and the use of image recognition technology to identify weeds has always been a research hotspot. [0003] Since identifying weeds through image processing technology requires a large number of mathematical calculations, the processor requirements are generally high. The traditional solution is that the UAV obtains the remote sensing...

AI Technical Summary

Problems solved by technology

The traditional solution is that the UAV obtains the remote sensing image of the corresponding rice area through the operation of the user. After the collection is completed, the acquired remote sensing image is removed from the storage on the UAV, and the server is used for image recognition processing. , and then manually mark the rice weed area of ​​the processed image, which is not conducive to the user's efficient, real-time, and intuitive observation of the weed recognition results

Images