Abstract
This paper describes the development of a modular unmanned aerial vehicle for the detection and eradication of weeds on farmland. Precision agriculture entails solving the problem of poor agricultural yield due to competition for nutrients by weeds and provides a faster approach to eliminating the problematic weeds using emerging technologies. This research has addressed the aforementioned problem. A quadcopter was built, and components were assembled with light-weight materials. The system consists of the electric motor, electronic speed controller, propellers, frame, lithium polymer (li-po) battery, flight controller, a global positioning system (GPS), and receiver. A sprayer module which consists of a relay, Raspberry Pi 3, spray pump, 12 V DC source, water hose, and the tank was built. It operated in such a way that when a weed is detected based on the deep learning algorithms deployed on the Raspberry Pi, general purpose input/output (GPIO) 17 or GPIO 18 (of the Raspberry Pi) were activated to supply 3.3 V, which turned on a DC relay to spray herbicides accordingly. The sprayer module was mounted on the quadcopter and from the test-running operation conducted, broadleaf and grass weeds were accurately detected and the spraying of herbicides according to the weed type occurred in less than a second.
Highlights
Farmers are often faced with the challenges of eradicating weeds on farmland
This research work provides details on the development of a smartweed detector and selective herbicide sprayer that detects and sprays weeds on farmland. This was achieved by deploying deep learning algorithms on an embedded system mounted on a quadcopter
The convolutional neural networks (CNN) model was converted to TensorFlow lite format and deployed on the Raspberry Pi 3
Summary
Farmers are often faced with the challenges of eradicating weeds on farmland. Weeds are unwanted plants which compete with crops for water, light, nutrient, and space on farmland. Local farmers in developing countries often use the traditional weed control methods, which involve manual removal of weeds and manual application of herbicides on a large agricultural field, which is laborious, time-wasting, and often leads to environmental pollution. In this era of the fourth industrial revolution, sophisticated technologies which involve the use of flying and ground robots in spraying herbicides, have become necessary. Precision or smart agriculture involves optimizing agricultural processes, real-time analysis, and monitoring of agricultural data [1]. According to Miranda et al [3], the word “smart” relates to the ability of a system to integrate control and actuation tasks in analyzing situations to make real-time decisions given available data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
