High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Iot and Wireless Sensor Network Based Weed Detection and Removal by Autonomous Farming Robot

Author(s):

Prasad Tengale , S.B.Patil College of Engineering ; Saurabh Burungle, S.B.Patil College of Engineering ; Prathmesh More, S.B.Patil College of Engineering

Keywords:

Artificial Intelligence (AI), Convolutional Neural Network (CNN), Internet of Things (IoT), ConvNet, Cloud Computing

Abstract

Small-scale farming and gardening benefit from the assistance of robots. This can be accomplished with the use of artificial intelligence integrated into robots, thereby benefiting farmers. Drones equipped with thermal cameras can interact with crops by sensing and spraying water, organic fertilizers, and pesticides automatically using an Artificial Intelligence (AI) method. The proposed model also includes a function in which, when birds attack crops, an active piezoelectric buzzer and a controller enable the drones to detect and move against the birds with a loud noise to drive them away, preventing crop damage. Crop health monitoring is the third component of the project. The crops health is assessed using a robotic arm mounted on a moving vehicle and an image sensor that moves across the field or garden. Using image processing, the arm photographs the crops, analyses crop patterns, and finds bugs and pests (binary inversion, dilation). The database for the same is being established, and it may contain information about pests, illnesses, growth conditions, and climatic aspects. The Machine Learning approach is used to train the drone to make decisions and spray pesticides automatically. Finally, using delta robots and robotic arms, the collected veggies and fruits are freshly packed. This avoids the processing stage and adulteration, retaining 100 percent of the nutrition. This method will have a huge impact on the future of organic farming.

Other Details

Paper ID: IJSRDV10I20064
Published in: Volume : 10, Issue : 2
Publication Date: 01/05/2022
Page(s): 76-78

Article Preview

Download Article