IOT and Machine Learning based System for Banana Diseases and Pest Detection
In some recent years, AI has grown so far. It has been acquired its place in nearly all the industries. From the beginning of the last decade, a tremendous breakthrough is seen in the agriculture industry. We are living in a developing country of a mixed economy where a huge contribution has made by
2025-06-28 16:33:22 - Adil Khan
IOT and Machine Learning based System for Banana Diseases and Pest Detection
Project Area of Specialization Artificial IntelligenceProject SummaryIn some recent years, AI has grown so far. It has been acquired its place in nearly all the industries. From the beginning of the last decade, a tremendous breakthrough is seen in the agriculture industry. We are living in a developing country of a mixed economy where a huge contribution has made by the agriculture sector. The quality of agriculture products depends upon many factors. One of the most important factors to maintain a good quality of the plant and product is by consequently, minimizing plant diseases which ensure the quality and quantity of the production. In countries like our`s where agricultural production is continuously decreasing because of many reasons like climate change, plant diseases, pests etc., we need to innovate and come up with ideas and solutions to increase yield as well as quality.
Banana disease and pest detection are one of the steps to integrate artificial intelligence into agriculture. Since, Banana is the most popular marketable fruit crop grown all over the world throughout the year, and a dominant staple food in many developing countries. Worldwide, banana production is affected by numerous diseases and pests. Novel and rapid methods for the timely detection of pests and diseases will allow to surveil and develop control measures with greater efficiency. This project is based on the real life Machine Learning application. We aim to develop an AI and IOT based banana disease and pest detection system to support banana growers.
The model uses a machine learning algorithm to detect diseases in the banana plant such as banana bacterial wilt (BBW) and banana black Sigatoka (BBS) that have caused a huge loss to many banana growers. The technique led to the development of an approach that consists of many phases. In phase one, images were acquired using a standard digital camera. Phase two is the preprocessing phase where resizing and morphological operations occur. Next phase is the segmentation phase which translates to the conversion to a greyscale image if needed. Next is the feature extraction phase where extraction of features like colour, texture and, shape occurs and after that, it is compared with the trained dataset. Lastly, we have results that whether there is a diseased or not which then send to a server or IP address for remote access.
Project Objectives- Get the real-time image/stream of a banana plant.
- Process it using Machine Learning.
- Detect and recognize different diseases.
- Identify pests, harming the plant health and product quality.
- Recommend the treatment and pesticides for disease and pests respectively.
- Implement IOT by Keep sending the real time results to a server or IP address.
The process starts with the data collection ( samples ) followed by the labelling of diseases and pests. Then the data will be split in 80%, 20% partition. The machine learning model will be trained using 80% of that and will be tested by 20%. All the data so far collected will be stored in suitable storage. Then from the storage, we will process the data ( resized and reshaped ) as per the requirement of our model.
After we are done making the model, we will train our model as shown in the flowchart. Now we will provide it with an appropriate image which will go through image processing to reshape and resize then in the second step its features will be extracted after that the image will be given to the model for label prediction. Finally, we get the predicted label the rest of the information will be given with the label.
- Commercial:
The idea of applying advanced AI and IOT based robotics in agriculture is getting tremendous attention nowadays, as it provides ease in remote monitoring, higher quality of fresh produce, lower production costs, and the lesser need for manual labour.
- Farming:
The project will solve critical farm labour challenges by augmenting or removing manual work and reducing the need for large numbers of workers and help in increasing the production of healthy crops.
- Value Generation:
Despite being all season fruit, banana production is highly affected by numerous diseases and pests. This project will ensure the lesser produce wastage and plant care with high tech AI based disease and pest detection and cure recommendation.
- Time saving:
The traditional diagnosing method is a lot of time consuming. In the traditional method, Diagnoses is done by field officers, who come from different cities and have many fields in line to visit. Till field officers visit the field, many crops would be affected by disease till then. As are some diseases that can destroy the crop in one day even before the field officer come to visit for diagnoses.
- Higher Accuracy:
Accuracy is not certain in manual diagnosis as the manual diagnosis is done by field officers who can make mistakes due to many factors. But in this project accuracy issue taken into context and a machine learning-based model is developed to overcome all previously described accuracy issues and will certainly provide better results than a human can.
- Cure Recommendation:
Along with determining diseases of crops, our model will give the best suited treatment/pesticide required for our diseased plant.
- More production:
With the enhancement of Agricultural Robotics, the opportunities have been increased for growing farms and fields as it reduces the manual work, ultimately affect the production positively, which will be beneficial for farmers as well as for a country’s GDP.
Technical Details of Final DeliverableOur final product will be a hardware and software based application which will process captured images of banana plant and fruit. The model will process the image for enrichment first, then texture and colour Feature extraction techniques are used to extract features such as boundary, shape, colour and texture for the disease spots to recognize the diseases, along with disease detection, it will also recognize the pest that causes disease. After recognizing diseases and pests, our model will finally provide a certain pesticide and recommendation that will help to get rid of the disease.
For all the detail discussed above, we will be using machine learning based algorithms. We will take real time image of the banana plant and fruit and provide it to our modelled software which will first process the image and make it suitable for further processing. Then the image will go to our trained model which will then process the given data and predict disease, pest and cure for the plant and fruit. The results then send to a server or an IP Address for remote observation and monitoring. As per the hardware, we are primarily implementing machine learning using Raspberry Pi and camera. After that when we are done with ML, we will build an IOT based field vehicle prototype as a platform using ESP32 on which we implement our ML hardware along with vehicle assemblies. The vehicle is remotely controlled by the user using a mobile App. In the end, the user remotely has real time results from the vehicle camera which is rovering in the field.
Final Deliverable of the Project HW/SW integrated systemCore Industry AgricultureOther Industries IT Core Technology Artificial Intelligence(AI)Other Technologies Internet of Things (IoT)Sustainable Development Goals Good Health and Well-Being for People, Decent Work and Economic Growth, Responsible Consumption and Production, Climate Action, Life on LandRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 70000 | |||
| Raspberry pi | Equipment | 1 | 12000 | 12000 |
| ESP32 | Equipment | 1 | 2000 | 2000 |
| Camera | Equipment | 1 | 5000 | 5000 |
| Micro SD Card | Equipment | 1 | 3000 | 3000 |
| Prototype Vehicle Chases | Equipment | 1 | 5000 | 5000 |
| Wheel Motors | Equipment | 4 | 5000 | 20000 |
| Linear Actuator | Equipment | 1 | 5000 | 5000 |
| Servo Motor | Equipment | 1 | 2000 | 2000 |
| Battery | Equipment | 1 | 2000 | 2000 |
| Solar Panel | Equipment | 1 | 2000 | 2000 |
| Solar Battery Charger | Equipment | 1 | 2000 | 2000 |
| Minor pieces of Stuff | Miscellaneous | 1 | 4000 | 4000 |
| Travelling | Miscellaneous | 1 | 6000 | 6000 |