Plant Disease Detection Robot

The robot helps the farmer to take informed decision locally or allows connecting with other existing services. This agri-robo find diseases on various infected leafs. This system result in detection of cotton 

Project Title

Plant Disease Detection Robot

Project Area of Specialization

Robotics

Project Summary

The robot helps the farmer to take informed decision locally or allows connecting with other existing services. This agri-robo find diseases on various infected leafs. This system result in detection of cotton diseases and spray the pesticides of disease in proper amount when needed.

Project Objectives

1. To construct a robot.
2. To develop a navigation system without damaging any crops.
3. To create our own image data set for detection of plant diseases.
4. To extract the important area known as ROI (Region of interest) of the image by using segmentation methods to detect the plant disease.
5. To identify the type of disease the plant is affected with by using classifiers and by matching it with our own created data set.
6. To acquire the pinpoint location of the affected plant.
7. To develop a system free from human interference.
8. To send the location of the affected plant and the disease of the plant by which it is affected through message.
9. To improve the yield of the crops.
10. To introduce the farmers with modern technology and equipment.

Project Implementation Method

Working on the chassis, autonomous navigation, and image classifiction began imeediately and progressed at a good pace. Where we ran into major unexpected challenges and delays related to our chassis and drive system. Simply put we did not anticipate such varying terrains among the test greenhouses, and motors, wheels, wiring, controls, etc. that were fine in scenario A were overwhelmed in scenario B. We went through a large number of mods to dial-in a workable chassis for all of our environments. We had to make a lot of time and budget constraints but the end product exceeded our initial goal of a minimum viable configuration. The final design at the time of submission is described below.

To be able to look at raised beds of plants and potentially upgrade to a moving camera that could look at the top and bottom of tomato plants, we built a camera pole using a carbon fiber rod bought from a garage sale. The rod was fitted with 2 3D-printed clamps for the navigation and classification cameras. We also added 1.2v solar lighting to the pole, as well as, 12v multicolor status lights on top of the pool. 

For classification we used the MobileNet SSD model due to its relatively small size and the fact that it already had a method to upload to an android app.We got the data by using 5-10 second videos and created a script to extract images from these videos. The videos themselves had been places in folders named after the disease and the plant. We made sure to take these videos under different conditions and at different locations. The total training dataset consisted of about 2000 images.We also made a website to show the output of the classification and the the overall map of the greenhouse and its plant health. The website uses XML data to create this grid. We did not have time to add real time updates to the website from the classifier but it is one of our future goals. We also tested SMS system by Twillo to send a message to a phone when the plant disease is above a given threshold. Again due to time constraints, we have not connected it to the classifier yet.

Benefits of the Project

The robot moves around the field capturing the image of the leaf and also monitors the field condition that is controlled using an android application.

This robot helps in early detection of the disease and monitors the field condition that help the farmer in increasing the yield.

Technical Details of Final Deliverable

 we used the MobileNet SSD model due to its relatively small size and the fact that it already had a method to upload to an android app.We got the data by using 5-10 second videos and created a script to extract images from these videos. The videos themselves had been places in folders named after the disease and the plant. We made sure to take these videos under different conditions and at different locations. The total training dataset consisted of about 2000 images.We also made a website to show the output of the classification and the the overall map of the greenhouse and its plant health. The website uses XML data to create this grid. We did not have time to add real time updates to the website from the classifier but it is one of our future goals. We also tested SMS system by Twillo to send a message to a phone when the plant disease is above a given threshold. Again due to time constraints, we have not connected it to the classifier yet.

Final Deliverable of the Project

Hardware System

Core Industry

Agriculture

Other Industries

Core Technology

Robotics

Other Technologies

Sustainable Development Goals

Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com