Related Experiment Video
Updated: Oct 7, 2025
10:49
Visualizing Efficacy of Pesticides Against Disease Vector Mosquitoes in the Field
Published on: March 16, 2019
8.7K
Ag-YOLO: A Real-Time Low-Cost Detector for Precise Spraying With Case Study of Palms.
Zhenwang Qin1, Wensheng Wang1, Karl-Heinz Dammer2
1Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China.
Frontiers in Plant Science
|January 10, 2022
Summary
This study introduces Ag-YOLO, a computer vision system for drones, enabling precise pesticide spraying in challenging terrains. The efficient, low-cost system enhances precision agriculture capabilities.
Area of Science:
- Agricultural Engineering
- Computer Vision
- Robotics
Background:
- Unmanned aerial vehicles (UAVs) are used in precision agriculture (PA) for monitoring and spraying.
- Effective and safe pesticide application in small or rugged fields remains a challenge.
Purpose of the Study:
- To develop a low-cost, energy-efficient onboard computer vision (CV) system for UAVs.
- To enable synchronized crop monitoring and precise spraying in difficult environments.
Main Methods:
- Developed an object detection algorithm, Ag-YOLO, inspired by YOLO.
- Utilized an Intel Neural Compute Stick 2 (NCS2) as the hardware component.
- Trained and tested the system using aerial images of areca plantations.
Main Results:
- Ag-YOLO achieved high accuracy (F1 score = 0.9205) and speed (36.5 fps) on the NCS2.
- The system is lightweight (18g), low power (1.5W), and cost-effective (~$66).
- Ag-YOLO is 2x faster and uses 12x fewer parameters than YOLOv3-Tiny.
Conclusions:
- The developed CV system provides a viable solution for precise pesticide spraying in challenging agricultural settings.
- Synchronizing crop monitoring and spraying enhances the efficiency and precision of PA.
- This technology supports smarter farming practices in diverse terrains.
