A Perception System for an Autonomous Pesticide Boom Sprayer

• Gustavo do Nascimento FURG
• Felipe Weber FURG
• Gabrielle Almeida FURG
• Fábio Terra IFSUL
• Paulo Drews FURG

Resumo

Over the past few years, agriculture has undergone profound changes due to technological advances. The application of agrochemicals revolutionized agriculture by reducing manpower, increasing the productivity and providing a greater control of spontaneous plants. However, the application of pesticides using boom sprayers remain the same even though the advances in autonomous tractors. As crops are usually planted in rows, this paper optimizes and automates the application of pesticides through an autonomous system based on local information using computer vision. The system is implemented on smartphones and is capable of detecting rows in plantations, activating the related sprayer nozzles. Additionally, the system is easy to install in many types of tractor-mounted boom sprayers. Experimental results using computer vision are obtained in an onion family farming where the system detects planting lines and controls the nozzles.

Palavras-chave: Agriculture, Robots, Agricultural machinery, Image segmentation, Covariance matrices, Eigenvalues and eigenfunctions, Cameras