Crop Duster

The project is completely described by using references and diagrams. The purpose of this system is to make a farmer and a average person life more easier where they can use this device to easily detect disease or pest in plant or leaf and eradicate it by spray pest repellent on it just by putting d

Project Title

Crop Duster

Project Area of Specialization

Artificial Intelligence

Project Summary

The project is completely described by using references and diagrams. The purpose of this system is to make a farmer and a average person life more easier where they can use this device to easily detect disease or pest in plant or leaf and eradicate it by spray pest repellent on it just by putting device’s camera in front of leaf from particular angle. This system is not only convenient for disease detection but it will also keep plants healthy by preventing it from insects and locusts and increase yearly yield.

The primary goal of the Department of horticulture is to offer pace to the development pace of agribusiness improvement and harvest age and efficiency which will fortify the financial status of the ranchers and inspire their way of life. Agribusiness is polished to deliver food and other human needs, for example, food, security, medicines, tools, decorations, and for the most part a lot all the more including domesticated animals’ supplies. It is in like manner rehearsed as a business for monetary increase.

A lot of information from crop stands. AI strategies can investigate high dimensional Over the most recent 25 years, the detecting advances utilized in accuracy farming have progressed significantly creating information with obscure measurable attributes for exactness crop insurance by gaining the model structure straightforwardly from preparing information. The conversation of AI centers around various calculations however the procedure of highlight choice is significant. Persuading examination approaches to consolidate a reasonable element extraction and choice with suitable forecast calculations. We are toward the start of promising advancement which is profoundly pertinent to the improvement of harvest yields. Because of the momentum research elements in detecting advances and strategies for information examination, the accompanying patterns for the fate of information investigation in exactness crop security are normal. Irresistible plant maladies square measure brought about by pathogens, living microorganisms that contaminate a plant and deny it of supplements. Microbes, organisms, nematodes, mycoplasmas, infections and viroid's square measure the living specialists that cause plant disease.

Feasibility in agriculture makes life simpler for gracefully and request. It expanding step by step as request is expanding so stock expanded and for Increasing flexibly some technique we have to utilize and improve quality and amount by these measures.

Project Objectives

Agriculture is very labor-intensive field and only field where the robot is not used presently. Agriculture is the mainstay of the Pakistan economy. Almost 70% people depend on it & shares major part of the GDP. Diseases in crops mostly on the leaf’s effects on the reduction of both quality and quantity of agricultural products.

Perception of human eye is not so much stronger so as to observe minute variation in the infected part of leaf. In this we are using image processing techniques to classify diseases & quickly diagnosis can be carried out as per disease. Here we are designing autonomous intelligent farming system which indicates the plant health and spray suitable fungicides with the shooters. Designing autonomous intelligent farming system which indicates the plant health by observing the color of their leaves by image processing. Image processing is done by the Raspberry pi. This robot takes images of crop and by using image processing in raspberry pi find out the disease present or not on crop leaf. Robot shows the name of the disease and suitable fertilizer accordingly and at last spray the defined fertilizer on crop by using robot.

Different type of leaf diseases on plant determines the quality, quantity, and stability of yield. The primary goal of the Department of horticulture is to offer pace to the development pace of agribusiness improvement and harvest age and efficiency which will fortify the financial status of the ranchers and inspire their way of life. Agribusiness is polished to deliver food and other human needs, for example, food, security, medicines, tools, decorations, and for the most part a lot all the more including domesticated animals’ supplies. It is in like manner rehearsed as a business for monetary increase. International Conference on Learning Representations (ICLR) and Consultative Group on International Agricultural Research (CGIAR) jointly conducted a challenge where over 800 data scientists globally competed to detect diseases in crops based on close shot pictures. The objective of this challenge is to build a machine learning algorithm to correctly classify if a plant is healthy, has stem rust, or has leaf rust. Wheat rust is a devastating plant disease affecting many crops, reducing yields and affecting the livelihoods of farmers and decreasing food security across Africa. The disease is difficult to monitor at a large scale, making it difficult to control and eradicate. An accurate image recognition model that can detect wheat rust from any image will enable a crowd-sourced approach to monitor crops.

Project Implementation Method

System consists on a Raspberry Pi (4) a series of small single board computer, Plant disease detection script is run on raspberry Pi which returns healthy or infected as an output. Relay 5V module is used to switch on or off if the script returns infected or healthy receptively. Then the motor pump 12V sprays the pest repellent on plants. Raspberry Pi: Used to execute plant disease detection script and output instruction. Raspberry Pi is equipped with built in USB, Wi-Fi, HDMI and with forty GPIO pins. All pins are used to linked with other electronic devices via jumper wires. It allows the designers to control and sense the external electronic devices in the real world. Relay: Works as Switch between raspberry Pi and motor pump. Relay is a device worked on the principle of electromagnetic induction. It is basically a switch.

Motor Pump and Jet Nozzle: Used to spray pest repellent.

Software Implementation - Thonny python IDE: Used for programming. The Pi Integrated Development Environment - or Thonny (IDE) - contains a text editor for writing code, a message area, a text console, a toolbar with buttons for common functions and a series of menus. It connects the Raspberry Pi to hardware via GPIO pins to communicate with them. Different images and details are discussed that are being used in project implementation. With the help of all these images and diagrams working of project can be understandable and working of system can be determined. Testing of the system is done in following steps. Plants disease detection script and each component of the system is tested separately to determine if it is working properly and giving us desired results. The components are then integrated with each other with the help of python programming using a Thonny IDE. Fig 6.5a and 6.5b shows the coding done in Redberry Pi. After all components are tested, they are connected with each other and complete system is made. The system works fine and fulfill our requirements.

Development life cycle of the project is as follows, Gathering and analyzing requirements. i.e., scope of the project, data-set and reading research papers. Designing the circuit and structure. Implementation of the algorithm with components i.e., Camera, Single Channel Relay. Testing the system for working normally through input various images from the test-set. Overcome short comings in the recognition and response time. The device gets switch on it starts capturing image (captured image after every 10 seconds) via camera, once it recognizes the leaf in image it sends the instruction to turn-on the motor through single-channel-relay and sprays the pest repellent using jet nozzle.

Benefits of the Project

The application of artificial intelligence techniques and methodologies sparked the interest of the scientific community, since they constitute the appropriate tools to deal with the noisy and sometimes chaotic nature of cotton's yield production and lead to more accurate predictions. Along this line, research focused on the development of expert systems for the prediction of agriculture production for assisting growth operations. These intelligent systems exploit the high predictive ability of machine learning algorithms, focusing on increasing crop's efficiency and economic benefits, while simultaneously reducing risks and losses. Species selection is a tedious process of searching for specific genes that determine the effectiveness of water and nutrients use, adaptation to climate change, disease resistance, as well as nutrients content or a better taste. Machine learning, in particular, deep learning algorithms, take decades of field data to analyze crops performance in various climates and new characteristics developed in the process. Based on this data they can build a probability model that would predict which genes will most likely contribute a beneficial trait to a plant.

While the traditional human approach for plant classification would be to compare color and shape of leaves, machine learning can provide more accurate and faster results analyzing the leaf vein morphology which carries more information about the leaf properties. The accurate detection and classification of crop quality characteristics can increase product price and reduce waste. In comparison with the human experts, machines can make use of seemingly meaningless data and interconnections to reveal new qualities playing role in the overall quality of the crops and to detect them. Both in open-air and greenhouse conditions, the most widely used practice in pest and disease control is to uniformly spray pesticides over the cropping area. To be effective, this approach requires significant amounts of pesticides which results in a high financial and significant environmental cost. ML is used as a part of the general precision agriculture management, where agro-chemicals input is targeted in terms of time, place and affected plants. Agriculture is the mainstay of the Pakistan economy. Almost 70% people depend on it & shares major part of the GDP. Diseases in crops mostly on the leaf’s effects on the reduction of both quality and quantity of agricultural products. Perception of human eye is not so much stronger so as to observe minute variation in the infected part of leaf.

Technical Details of Final Deliverable

Technical details of Hardware used are as follows:

Specifications of Hardware.

Specifications of Software.

Use Case Diagram

Fig 5.3 below shows the use case diagram whenever the device gets switch on it starts capturing image (captured image after every 10 seconds) via camera, once it recognizes the leaf in image it sends the instruction to turn-on the motor through single-channel-relay and sprays the pest repellent using jet nozzle.

Fig 5.3 Use case diagram

Sequence Diagram

Fig 5.4 below shows the sequence diagram of the project from first step to last step.

Fig 5.4 Sequence Diagram

Flow Chart

Fig 5.6 below shows the flow chart of the system

Fig 5.6 Flow Chart

Circuit Diagram

Fig 5.7 Circuit Diagram of project

TYPE OF HARDWARE

System on chip (SoC)

CPU

Instruction set

RAM

Storage Slot

Ethernet

Wireless

USB Port

GPIO

Power Source

Camera

Single channel-relay-module

Motor Pump

TYPE OF SOFTWARE

Programming Language

Algorithm

Packages/Libraries

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Agriculture

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Decent Work and Economic Growth

Required Resources

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