Mini-Drones in Automated and Energy-Efficient Fruit Harvesting

Disciplines

Agriculture | Electrical and Computer Engineering | Mechanical Engineering | Robotics

Abstract (300 words maximum)

This project is poised to revolutionize agriculture by automating fruit harvesting through the use of intelligent mini-drones equipped with an onboard camera. This camera is powered by a specialized technology called YOLOv5, a Convolutional Neural Network (CNN) designed for real-time object detection. The YOLOv5 CNN has been meticulously trained to recognize specific fruits such as grapes and tomatoes, with tomatoes being the primary focus of this project. These smart drones collaborate with a mobile drone, similar to a smartcar, which processes the camera data and assists in fruit collection. The onboard camera on the smart drones plays a pivotal role in accurately identifying ripe fruits on plants. Once a fruit is detected, the drones delicately sever it from the plant, allowing it to fall gently to the ground. Subsequently, the mobile drone efficiently collects these harvested fruits. Central to this research is the utilization of the onboard camera and the YOLOv5 CNN technology. These advancements ensure precise fruit recognition and enable the drones to operate efficiently without frequent recharging. The project emphasizes the seamless integration of this smart camera, sophisticated YOLOv5 algorithm, and drone systems, creating a cohesive and efficient harvesting process. Beyond the realm of agriculture, this research addresses critical challenges such as labor shortages and high operational costs associated with manual fruit harvesting. Moreover, the automation of farming practices contributes to environmental sustainability by reducing the ecological impact of traditional farming methods. In summary, our project demonstrates the practical application of the onboard camera and YOLOv5 CNN technology in automating fruit harvesting. By leveraging these innovations, we showcase the feasibility of efficient, technology-driven agriculture. This initiative marks a significant step toward a sustainable and automated future in farming practices.

Academic department under which the project should be listed

SPCEET - Electrical and Computer Engineering

Primary Investigator (PI) Name

Yan Fang

This document is currently not available here.

Share

COinS
 

Mini-Drones in Automated and Energy-Efficient Fruit Harvesting

This project is poised to revolutionize agriculture by automating fruit harvesting through the use of intelligent mini-drones equipped with an onboard camera. This camera is powered by a specialized technology called YOLOv5, a Convolutional Neural Network (CNN) designed for real-time object detection. The YOLOv5 CNN has been meticulously trained to recognize specific fruits such as grapes and tomatoes, with tomatoes being the primary focus of this project. These smart drones collaborate with a mobile drone, similar to a smartcar, which processes the camera data and assists in fruit collection. The onboard camera on the smart drones plays a pivotal role in accurately identifying ripe fruits on plants. Once a fruit is detected, the drones delicately sever it from the plant, allowing it to fall gently to the ground. Subsequently, the mobile drone efficiently collects these harvested fruits. Central to this research is the utilization of the onboard camera and the YOLOv5 CNN technology. These advancements ensure precise fruit recognition and enable the drones to operate efficiently without frequent recharging. The project emphasizes the seamless integration of this smart camera, sophisticated YOLOv5 algorithm, and drone systems, creating a cohesive and efficient harvesting process. Beyond the realm of agriculture, this research addresses critical challenges such as labor shortages and high operational costs associated with manual fruit harvesting. Moreover, the automation of farming practices contributes to environmental sustainability by reducing the ecological impact of traditional farming methods. In summary, our project demonstrates the practical application of the onboard camera and YOLOv5 CNN technology in automating fruit harvesting. By leveraging these innovations, we showcase the feasibility of efficient, technology-driven agriculture. This initiative marks a significant step toward a sustainable and automated future in farming practices.