https://github.com/jonsonkurt/yolov5-based-plant-disease-detection

Plant Monitoring System with Animal Intrusion Detection is a prototype developed to help farmers and gardeners address the challenges posed by plant health and animal intrusions. The system employs machine learning algorithms, a computer, a microcontroller, and a camera to provide an effective monitoring tool for plant health and animal intrusion.
https://github.com/jonsonkurt/yolov5-based-plant-disease-detection

Last synced: 27 days ago
JSON representation

Plant Monitoring System with Animal Intrusion Detection is a prototype developed to help farmers and gardeners address the challenges posed by plant health and animal intrusions. The system employs machine learning algorithms, a computer, a microcontroller, and a camera to provide an effective monitoring tool for plant health and animal intrusion.

• Host: GitHub
• URL: https://github.com/jonsonkurt/yolov5-based-plant-disease-detection
• Owner: jonsonkurt
• Created: 2023-01-11T11:06:35.000Z (almost 2 years ago)
• Default Branch: master
• Last Pushed: 2023-02-15T13:08:50.000Z (almost 2 years ago)
• Last Synced: 2024-10-15T06:45:22.203Z (2 months ago)
• Language: Python
• Homepage:
• Size: 15.4 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
 Plant Monitoring System with Animal Intrusion Detection 


The Plant Monitoring System with Animal Intrusion Detection is a prototype developed to help farmers and gardeners address the challenges posed by plant health and animal intrusions. The system employs machine learning algorithms, a computer, a microcontroller, and a camera to provide an effective monitoring tool for plant health and animal intrusions.

The YOLOv5 model is used to detect leaf blight disease with a mean average precision of 38.80% (mAP 0.5) and 13.3% (mAP 0.5:0.95), resulting in a precision of 56% and a recall of 37.90%. Additionally, a motion sensor and laser tripwire are included in the system for detecting animal intrusions with high accuracy rates of 90% and 95%.

In the event of any detections, the system sends real-time SMS alerts to farmers, allowing them to take appropriate action promptly. This system has the potential to significantly improve farming productivity and sustainability, and additional evaluation is necessary to validate accuracy. Further testing with a larger sample size may be required to improve accuracy, and adjusting the confidence level may also lead to better results.

![329080626_3444203832567977_7573930755452693176_n](https://user-images.githubusercontent.com/55541726/219035014-0be8ddf8-d551-4e72-bfb4-97c0c82e295a.png)

Plant Monitoring Application Dashboard

![Screenshot 2023-02-15 210348](https://user-images.githubusercontent.com/55541726/219035041-6858dc40-5661-4b9b-a2fa-ca8d711f8eda.jpg)

Set Capturing Time Feature of the Application

![schematic diagram](https://user-images.githubusercontent.com/55541726/219035563-b0faa141-ccb8-4a57-8edc-a100fd37fa78.png)

Schematic Diagram of the System