Automatic Crop Disease Detection And Spray Machine

Wheat yellow rust is one of the most destructive diseases in wheat production and significantly affects wheat quality and yield. Accurate and non-destructive identification of yellow rust is critical to wheat production management. The image processing technique with the real-time machine vision sys

Project Title

Automatic Crop Disease Detection And Spray Machine

Project Area of Specialization

Mechanical Engineering

Project Summary

Wheat yellow rust is one of the most destructive diseases in wheat production and significantly affects wheat quality and yield. Accurate and non-destructive identification of yellow rust is critical to wheat production management. The image processing technique with the real-time machine vision system is one of the most commonly used on-the-go target detection methods for variable-rate spraying. Its high precision, quick response, and low input cost are made it more popular and widely acceptable in the area of agricultural automation. Detection of disease by naked eye is very inaccurate and it required lot of team effort and experts, which is much more expansive. So automatic leaf disease detection system is required. Automatic leaf disease detection system is very accurate and it take very less time to detect disease in plant that can spray pesticides in restricted quantities. Using this form of robots Time consumption is decreased in spraying the pesticide liquid and it will also assist farmers to decrease the workload and in any season and conditions to do job.

In this process of leaf disease detection firstly we are going to acquired normal image by the means of any digital camera. Acquiring the leaf image is first step in leaf disease detection. Secondly we are going for pre-processing of image. In this we are going to enhance the image quality. After enhancing the image we divide the image in different cluster. In that green pixel are masked and only infected portion left.

Project Objectives

Agriculture is the backbone of Pakistan economy and now a days many diseases occur in plant and it impact very badly on farmers and Pakistan economy. So detection of plant disease is very important. If proper care not taken in this area then it causes serious effect on plants and due to which respective product quality, quantity or productivity is effected. Detection of plant disease through some automatic technique is beneficial as it reduces a large work of monitoring in big farms of crops, and at very early stage itself it detects the symptoms of disease i.e. when they appear on plant leaves.

The functional block diagram of the developed variable-rate chemical spraying system is shown in Fig. 1.

         

                                                Figure 1. Functional block Diagram

Project Implementation Method

Initially, the web camera captures the paddy plant image and stores it in the laptop, where the lesion region of plant leaves is identified. The processed output in terms of disease severity is determined using the developed image processing algorithm.

The following are the steps for plant leaf disease detection using  image processing:

1.Image Acquisition:

Image acquisition is the first method of digital image processing and it is described as capturing the image through digital camera and stores it in digital media for further MATLAB operations. It is also an action of retrieving an image from hardware, so it can be passed through further process. In our work, using digital camera we captured healthy and diseased images of wheat leaf as shown in fig.2

                                                     Figure 2. Disease image of wheat leaf

2.Image Pre-processing:

Input image what we captured is not always satisfying always there is some noise is added in that image, so for removal of noise and getting informative image we apply preprocessing technique. In this process firstly the image is enhanced after smoothing. While collecting image many information is collected which include noise. To remove noise we use different type of filtering techniques. Mainly this process contain three main steps clipping, smoothing and enhancement.

          

                                                                Figure 3. leaf disease image

3. Image Segmentation:

Image segmentation is the process of partition of image into different segments. It use to get some meaningful information from segmented image. In this we are going to mask green pixels of image and remains with the infected portion of image. The procedure follows a simple and easy way to classify a given data set through a certain number of clusters.

The category of plant disease severity is decided according to threshold limits, and this information is then sent to the Adriano microcontroller. Further, it computes the required amount of chemical to be sprayed and the opening time duration for pump. After this, the microcontroller then sends a 5 VDC signal to the respective relay switch, which further control the 12 V/DC pump and the required amount of input chemical is sprayed on the diseased paddy plants.

Benefits of the Project

• An automatic plant-disease detection system provides clear benefit in monitoring of large fields, as this is the only approach that provides a chance to discover diseases at an early stage.
• Detection of plant disease through some automatic technique is beneficial as it reduces a large work of monitoring in big farms of crops, and at very early stage itself it detects the symptoms of diseases ,when they appear on plant leaves.
• identify the type of disease and pesticide to the disease.
• Identify the correct disease symptoms and understanding when to control these diseases.

Technical Details of Final Deliverable

Automatic spraying of pesticides is used to inject the pesticide into the targeted zone of the crops contaminated. This scheme is based on a web camera for image acquisition, a Laptop (8GB RAM, Intel Core i7 CPU, and Windows 10 operating system) for image processing; a plastic tank for pesticide storage purpose; a 12V pump; spray nozzles; relay switches; an Adriano Uno microcontroller board; and a 12V battery. All of these components were assembled on a cart for pesticide applications.

An Arduino Uno microcontroller board is used to control pump. One 12 V/DC In this model, a web camera is connected to the laptop through 1.5 m long USB  2.0 cables. The flat fan nozzle is positioned below the web camera to compensate the time lag between the image acquisition and the real-time spraying of pesticide. A 12 V/DC fixed displacement pump is used to maintain the flow of liquid inside supply tubes. relay switch is provided to ON/OFF pump according to the control signal received through the microcontroller. Power supply to the entire system is provided with the help of a 12 V/DC Sealed Lead Acid battery.. CAD model of crop disease detection and spray machine is shown in Figure 4.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Agriculture

Other Industries

Education , Food , Health

Core Technology

Artificial Intelligence(AI)

Other Technologies

Wearables and Implantables, Clean Tech

Sustainable Development Goals

Responsible Consumption and Production

Required Resources

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