DEPARTMENT OF INFORMATION

TECHNOLOGY

Micro-Project Report
(Capstone Project Planning)
AgroVision AI

Academic Year: 2024-25

Program Code: IF5I
Course: Capstone Project Planning
Course Code: 22058
Subject Teacher: Mrs. Suwarna Thakre
Group No:

ZAGDU SINGH CHARITABLE TRUST (REGD.)

THAKUR POLYTECHNIC
(An ISO 9001:2015 Certified Institute)
Thakur Complex, West to W. E. Highway, Kandivali, (E), Mumbai – 400 101
(Accredited by: National Board of Accreditation)

Department Of Information Technology, IF5I 1|P a g e

m

MAHARASHTRA STATE BOARD OF

TECHNICAL EDUCATION
Certificate
This is to certify that:

Harsh Chauhan – 06
Garvit Kanani – 17
Shreeraj Jagtap – 15
Soham Pawaskar – 50

of 5th Semester of Diploma in Information Technology of

Institute, Thakur Polytechnic (Code:0522) have completed the
Micro Project satisfactorily in Subject – CPP for the academic
year 2023-2024 as prescribed in the curriculum.

Place: Mumbai Enrolment No.: …………….

Date: ………….. Seat No.: ……………….

Seal of
Institute

Subject Teacher Head of the Department Principal

Department Of Information Technology, IF5I 2|P a g e

 Certificate
This is to certify that:

Harsh Chauhan – 2205220029

Garvit Kanani – 2205220041
Shreeraj Jagtap – 2205220038
Soham Pawaskar – 2205220081

From THAKUR POLYTECHNIC college has completed.

Project Guide/Mentor Head of the Department

Department Of Information Technology, IF5I 3|P a g e

 ACKNOWLEDGEMENT

This acknowledgment transcends the reality of formality when we would

like to express deep gratitude and respect to all those people behind the
screen who guided, inspired and helped me for the completion of our
project work.

This project would add as an asset to my academic profile. We express

our sincere gratitude to our respectful Principal Dr. S.M. Ganechari for
enabling us to make use of laboratory and library facilities liberally, that
helped us a long way in carrying out our project work successfully.

We consider ourselves lucky enough to get such a good project. This

project would add as an asset to my academic profile. We express our
gratitude to the help of the Head of the Department of Information
technology, Mrs. Suwarna Thakre, for her constant supervision,
guidance and co-operation throughout the project and we would like to
express our thankfulness to our project guide (subject teacher), Mr. Sumit
Parmar for her constant motivation and valuable help through theproject
work. We extend our sincere gratitude to our parents who have
encouraged us with their blessings to do this project successfully.

THANK YOU.

Department Of Information Technology, IF5I 4|P a g e

 Table of Contents
CHAPTER TITLE PAGE
NO. NO.
1. Introduction on AgroVision AI 6

1.1 General Introduction 6

1.2 Aim 6
1.3 Scope of the Project 7
1.4 Background of the Industry 7
1.5 Problem Statement 7
2. Literature survey for AgroVision AI 9

2.1 Introduction 9
2.2 Related Work 9
2.3 Method 10
2.4 Framework 12
3. Proposed Detailed methodology of solving Identified 13
problem with Action plan
3.1 Purpose/Goal 13
3.2 Proposed Methodology 14
3.3 Asset Limitations 15
3.4 Data Collection for teaching 15
3.5 Database Design and Analysis 15
4. Block Diagram 16
4.1 Block Diagram Proposed Design 16
4.2 Action Plan 16
5. Conclusion, Bibliography 17
5.1 Conclusion 17
5.2 Bibliography 17

Department Of Information Technology, IF5I 5|P a g e

Abstract :-
The agricultural sector is undergoing a transformative shift, driven by
advancements in Artificial Intelligence (AI). Agro Vision AI is a cutting-edge
approach that integrates AI with agronomy to improve crop yield, optimize
resource use, and ensure food security. Through sophisticated data analysis,
machine learning models, and computer vision, Agro Vision AI enables farmers
to make data-driven decisions, detect crop diseases early, and automate
irrigation and pest control systems. This technology enhances precision
agriculture by analyzing satellite imagery, drone footage, and real-time field
data to monitor soil health, predict weather patterns, and forecast crop
outcomes. The integration of AI with farming techniques not only reduces
operational costs but also promotes sustainable farming practices by minimizing
the use of fertilizers, pesticides, and water. Agro Vision AI holds the potential
to address the growing challenges of climate change, population growth, and
limited arable land, marking a significant leap towards the future of agriculture.

Department Of Information Technology, IF5I 6|P a g e

Chapter-1 Introduction to AgroVision AI

1.1 General Introduction :-

Agriculture has long been the backbone of economies worldwide, but with
growing challenges such as climate change, population expansion, and
shrinking arable land, traditional farming practices face limitations. Agro Vision
AI represents a breakthrough in agricultural innovation, leveraging the power of
Artificial Intelligence (AI) to address these pressing issues. This integration of
AI technologies with agricultural practices has led to the development of
smarter, more efficient, and sustainable farming solutions. Agro Vision AI
encompasses a range of AI-driven technologies including machine learning,
computer vision, data analytics, and automation. These technologies enable
precision farming, where farmers can optimize crop production by accurately
predicting and addressing the needs of their fields. Machine learning models
process vast amounts of data from sources such as soil sensors, drones, satellite
imagery, and weather stations.

1.2 Aim :-
The aim of Agro Vision AI is to revolutionize agriculture by integrating
artificial intelligence technologies to improve the efficiency, sustainability, and
productivity of farming practices. By utilizing machine learning, computer
vision, and data analytics, Agro Vision AI seeks to empower farmers with data-
driven insights, enabling them to make informed decisions regarding crop
management, resource optimization, and disease prevention. The ultimate goal
is to enhance food security, reduce environmental impact, and promote
sustainable farming practices, addressing the growing challenges of climate
change, population growth, and resource scarcity in the agricultural sector.

1.3 Scope of the project :-

The scope of Agro Vision AI extends across multiple aspects of modern
agriculture, encompassing precision farming, resource optimization, and
sustainability. It involves the use of AI technologies such as machine learning,
computer vision, and data analytics to address critical agricultural challenges

Department Of Information Technology, IF5I 7|P a g e

 1.4 Background of industry :-
The background of Agro Vision AI is rooted in the increasing need for
innovative solutions agriculture, driven by global challenges such as climate
change, population growth, and resource constraints. Traditional farming
methods, while effective for centuries, are no sufficient to meet the
demands of modern agriculture. This has led to the exploration of advanced
technologies, including Artificial Intelligence (AI), to enhance efficiency,
productivity, and sustainability.The concept of precision agriculture, which
forms the basis Agro Vision AI, began take shape in the late 20th century
with the development of remote sensing and Geographic Information
Systems (GIS).These technologies allowed farmers to gather data on soil
conditions, weather patterns, and crop health, enabling more informed
decision-making. However, the emergence of AI in the 21st century has
accelerated this by offering more sophisticated tools for data analysis and
automation.

1.5 Problem Statement :-

• Declining Agricultural Productivity: Traditional farming methods

struggle to meet the rising global food demand due to inefficient
resource use and outdated practices.
• Climate Change Impact: Unpredictable weather patterns, extreme
temperatures, and shifting climates are negatively affecting crop
yields and farming cycles.
• Pest and Disease Management: Farmers face challenges in
detecting and managing crop diseases and pest infestations early,
often resulting in major losses and increased use of harmful
pesticides.
• Sustainability Challenges: Overuse of chemicals, inefficient
resource management, and soil degradation are contributing to long-
term environmental harm, undermining the sustainability of
agricultural practices.

Department Of Information Technology, IF5I 8|P a g e

 Chapter-2 Literature survey on AgroVision AI

2.1 Introduction :-
Agriculture is the cornerstone of human civilization, providing the food,
fiber, and resources necessary to sustain growing populations. However,
modern agriculture faces unprecedented challenges, including climate
change, resource limitations, rising operational costs, and the need for
increased food production to meet global demand. Traditional farming
methods are increasingly proving inadequate in the face of these
complexities. As a result, innovative technologies are being explored to
enhance agricultural productivity and sustainability. One such innovation is
Agro Vision AI, a revolutionary approach that integrates Artificial
Intelligence (AI) with modern agricultural practices. Agro Vision AI
leverages advanced technologies such as machine learning, computer vision,
and big data analytics to optimize farming processes, predict crop outcomes,
manage pests and diseases, and improve resource efficiency. By harnessing
real-time data from sources such as sensors, drones, and satellites, Agro
Vision AI empowers farmers to make informed decisions, reduce waste, and
enhance productivity with precision.

2.2 Method :-
The methods employed by Agro Vision AI leverage a combination of
advanced technologies to optimize modern farming practices. Data
collection is fundamental, utilizing IoT sensors to gather real-time
information on soil health, moisture levels, and environmental conditions,
while drones and satellites capture aerial imagery of crop fields. These data
sources are integrated to provide farmers with a comprehensive
understanding of their land. Machine learning algorithms are then applied to
this data to create predictive models, helping farmers anticipate crop yields,
optimize irrigation schedules, and identify potential risks such as pest
infestations or disease outbreaks. Computer vision technology plays a
critical role in crop health monitoring, enabling AI-powered systems to
detect early signs of diseases and nutrient deficiencies from images captured
by drones and satellites. This real-time monitoring allows for precise,
targeted interventions, reducing the need for widespread pesticide use.
Furthermore, automated irrigation systems use AI models to control water
distribution based on soil moisture, plant needs, and weather forecasts,
ensuring efficient water use and preventing over- or under-watering

Department Of Information Technology, IF5I 9|P a g e

2.3 Framework :-
The framework of Agro Vision AI is built on a multi-layered approach that
integrates advanced technologies to streamline agricultural processes. At its
core, the framework involves data acquisition, where IoT sensors, drones, and
satellites continuously gather real-time data on key farming parameters such as
soil health, temperature, moisture, and crop conditions. This data feeds into the
data processing layer, where machine learning algorithms analyze and interpret
it, transforming raw inputs into actionable insights. AI models predict crop
yields, detect diseases, optimize irrigation, and manage resource allocation with
high precision. The next layer in the framework is decision support and
automation, which applies AI-driven insights to automate tasks such as
irrigation, fertilization, and pest control. Robotic systems are integrated into this
layer to perform labor-intensive activities like weeding, planting, and
harvesting, thus reducing human labor and increasing efficiency. Meanwhile,
computer vision systems continuously monitor crop health through visual
analysis, flagging early warning signs of disease or nutrient deficiencies.

Department Of Information Technology, IF5I 10 | P a g e

Chapter-3 Proposed Detailed methodology of solving
Identified problem Action plan

3.1 Purpose/Goal :-
The purpose of Agro Vision AI is to transform the agricultural landscape by
harnessing the power of artificial intelligence to address the pressing
challenges facing modern farming. Its primary goal is to enhance
productivity and sustainability in agriculture by providing farmers with
data-driven insights and automated solutions that optimize resource use,
improve crop yields, and reduce operational costs. By leveraging advanced
technologies such as machine learning, computer vision, and IoT sensors,
Agro Vision AI aims to empower farmers to make informed decisions
based on real-time data, enabling them to respond proactively to
environmental changes and agricultural threats. Furthermore, Agro Vision
AI seeks to promote sustainable farming practices that minimize
environmental impact, conserve water, and reduce reliance on harmful
chemicals.

3.2 Proposed Methodology :-

The proposed methodology for implementing Agro Vision AI is designed to
create an integrated approach that enhances agricultural practices through
data-driven insights and automation. It begins with data collection, utilizing
IoT sensors deployed in fields to monitor soil moisture, temperature, pH
levels, and nutrient content, complemented by drones and satellite imagery
to capture high-resolution images of crop health and growth patterns. This
data is then integrated into a centralized cloud-based database, where it
undergoes preprocessing to ensure accuracy and consistency for further
analysis. Next, machine learning models are developed to analyze both
historical and real-time data, enabling predictive analytics for crop yields,
disease detection, and irrigation optimization. Simultaneously, computer
vision algorithms are employed to assess drone and satellite imagery,
identifying early signs of crop diseases, nutrient deficiencies, and pest
infestations. The insights generated from this analysis are presented through
an analytics dashboard, providing farmers with visual representations of
trends and forecasts, along with automated alerts for critical conditions
requiring attention.

Department Of Information Technology, IF5I 11 | P a g e

3.3 Asset Limitations :-
Next, machine learning models are developed to analyze both historical and real-
time data, enabling predictive analytics for crop yields, disease detection, and
irrigation optimization. Simultaneously, computer vision algorithms are
employed to assess drone and satellite imagery, identifying early signs of crop
diseases, nutrient deficiencies, and pest infestations. The insights generated from
this analysis are presented through an analytics dashboard, providing farmers
with visual representations of trends and forecasts, along with automated alerts
for critical conditions requiring attention. Additionally, there is a lack of reliable
infrastructure in many agricultural areas, including insufficient internet
connectivity and limited access to power sources. This can impede the real-time
data collection and processing essential for the successful functioning of Agro
Vision AI systems. Furthermore, the technical expertise required to operate and
maintain these advanced systems may be lacking among farmers, necessitating
comprehensive training programs and ongoing support.

3.4 Database Design and Analysis :-

1. Objectives of Database Design: The primary objective of the database
design for Agro Vision AI is to create a robust, scalable, and efficient system
that can handle vast amounts of data collected from various sources such as IoT
sensors, drones, and external weather data. The database should facilitate real-
time data retrieval and analysis, support predictive modeling, and ensure data
integrity and security.
2. Data Normalization: To minimize redundancy and maintain data integrity,
the database will undergo normalization. This involves structuring the tables to
eliminate duplicate data and ensure that each piece of information is stored in a
single location. Typically, normalization will be conducted to at least the third
normal form (3NF).
3. Data Security and Privacy: Security measures will be implemented to
protect sensitive data. This includes:
• Role-based access control (RBAC) to limit who can view or modify data.
• Data encryption to safeguard information at rest and in transit.
• Regular audits and backups to ensure data recovery and integrity.

Department Of Information Technology, IF5I 12 | P a g e

3.5 Database Design and Analysis :-
1. Objectives:
• Create a robust, scalable database for real-time data handling.
• Support predictive modeling and ensure data integrity and security.
2. Key tables :-
• Farmers: Farmer ID, name, contact details, farm location.
• Sensors: Sensor ID, type, location, data collection frequency.
• Crop Health Data: Disease detection, nutrient levels, growth
stages.
3. Data Security and Privacy:
• Use data encryption for protection.
• Regular audits and backups for data integrity.

Department Of Information Technology, IF5I 13 | P a g e

 Chapter - 4 Block Diagram
4.1 Block Diagram Proposed Design :-

Agro Vision AI features a comprehensive system architecture that integrates

various components for effective agricultural management. At the forefront is
the Farmers (User Interface), which serves as the entry point for farmers to
access critical data, insights, and recommendations tailored to their needs. The
system collects essential Field Data, including information about field size, crop
type, and soil characteristics, alongside Crop Health Data, which monitors
factors such as disease presence and nutrient levels. Data is gathered through a
robust Data Collection process, utilizing methods such as drones for aerial
monitoring, satellite imagery for broad-scale assessments, and manual entry for
localized observations. This diverse range of data sources feeds into the
Centralized Database (RDBMS), which securely stores all collected information
and ensures efficient data retrieval and management. Complementing this, the
system integrates Weather Data to provide context for agricultural decisions,
enhancing the predictive capabilities of the system.The heart of the analysis lies
in the Machine Learning Models, which analyze both historical and real-time
data to forecast outcomes such as crop yields and pest infestations. The insights
generated are visualized through an Analytics & Reporting module, enabling
farmers to understand trends and make data-driven decisions. Finally, the
Decision Support System synthesizes information from various sources,
providing farmers with actionable recommendations that promote optimized
farming practices and improve overall productivity and sustainability in
agriculture. This holistic design aims to empower farmers with the tools and
insights necessary to thrive in an increasingly complex agricultural landscape.

Department Of Information Technology, IF5I 14 | P a g e

 4.2 Action Plan :-

Sr.No. Details of activity Planned Planned Name of

start date finished date responsible team
members
Soham Pawaskar,Garvit
1 Group Formation 01/08/2024 16/08/2024 Kanai,Shreeraj
Jagtap,Harsh Chauhan
Soham
Selection of three topics Pawaskar,Garvit
2 13/09/2024 13/09/2024
for Kanai,Shreeraj
presentation Jagtap,Harsh Chauhan

3 Selection of three topics 13/09/2024 13/09/2024 Shreeraj Jagtap

for
presentation
4 Presentation of three 25/09/2024 25/09/2024 Garvit Kanani
topics and final project
topic selection

5 Allotment of project 30/09/2024 30/09/2024 Soham Pawaskar

guide

6 Discussion with 07/10/2024 11/10/2024 Harsh Chauhan

project guide

7 Information 14/10/2024 11/10/2024 Garvit Kanani

Gathering

8 Literature Review 14/10/2024 18/10/2024 Soham Pawaskar

9 Project Proposal 21/10/2024 21/10/2024 Shreeraj Jagtap
Submission

10 Information books and 24/10/2024 24/10/2024 Harsh Chauhan

different websites

11 Seminar on the 28/10/2024 28/10/2024 Shreeraj Jagtap

finalized project
topic to the
project guide

Department Of Information Technology, IF5I 15 | P a g e

12 Study of 28/10/2024 28/10/2024 Soham Pawaskar,Garvit
technology
Kanai,Shreeraj Jagtap,Harsh
needed to
implement to Chauhan
three projects

13 Study of technology 31/10/2024 31/10/2024 Garvit Kanani

and software
components

14 Estimation of cost of 31/10/2024 04/11/2024 Soham Pawaskar

budget

15 Information 07/11/2024 07/11/2024 Harsh Chauhan

gathering and
documentation

16 Presentation to 08/11/2024 11/11/2024 Soham Pawaskar,Garvit

project guide
Kanai,Shreeraj Jagtap,Harsh
Chauhan

Department Of Information Technology, IF5I 16 | P a g e

Chapter-5 Conclusion, Bibliography

5.1 Conclusion :-
In summary, Agro Vision AI presents a promising solution to the challenges
faced in modern agriculture by integrating advanced technologies such as data
collection, machine learning, and analytics. The system aims to empower
farmers with actionable insights derived from comprehensive data analysis,
thereby enhancing crop management, optimizing resource utilization, and
improving overall agricultural productivity. Through a centralized database and
an intuitive user interface, Agro Vision AI facilitates the seamless flow of
information from field data and weather conditions to decision-making
processes. By harnessing the power of artificial intelligence, the system not only
addresses existing agricultural issues but also positions itself as a critical tool
for sustainable farming practices.

5.2 Biblography :-
• www.fao.org
• www.springer.com
• www.researchgate.net
• www.sciencedirect.com

Department Of Information Technology, IF5I 17 | P a g e