Course Overview

AI, IoT and Computer Vision for Smart Farming  

Duration: 8 to 12 Weeks (2 to 3 sessions per week) | 24-36 Direct Contact Laboratory and Interactive Seminar Hours (90 Notional Hours total)

Instructor(s): 

• Dr. Imran Mahmud : Professor and Head, Dept. of Software Engineering, Daffodil     International University

• Dr. Syed Md. Galib : Professor, Dept. of CSE, Jessore University of Science and Technology

• Fayazunnesa Chowdhury : Senior Lecturer, Dept. of Software Engineering, Daffodil International University 

• Md. Jahidul Alam : Lecturer, Dept. of CSE, Daffodil International University 

Course Description

This course addresses the emerging need for industry-oriented and research-focused education in Smart Farming by bringing together experts from industry and academia. It is designed to transform traditional mindsets by providing learners with a practical and comprehensive understanding of AI, IoT, Computer Vision, drones, and modern precision agriculture systems.

Evidence of Demand

The global agriculture sector is undergoing rapid digital transformation through Artificial Intelligence (AI), Internet of Things (IoT), Computer Vision, drones, and precision farming technologies. According to reports from the Food and Agriculture Organization (FAO), World Bank, and leading AgriTech market analyses, smart farming technologies are becoming essential for improving productivity, sustainability, food security, and resource optimization.

Bangladesh is experiencing growing demand for professionals capable of understanding and evaluating smart agriculture technologies, particularly in areas such as sensor-based monitoring, crop and livestock analytics, computer vision applications, and research-driven innovation. Universities, startups, agricultural enterprises, NGOs, and government agencies increasingly seek graduates with interdisciplinary knowledge combining agriculture and advanced computing technologies.

Course Objectives

Upon completion of the course, learners will be able to:

• Understand the role of IoT technologies in modern agriculture.
• Evaluate different agricultural sensors, communication technologies, and smart farming devices.
• Analyze computer vision applications for crop monitoring and livestock management.
• Explore pre-trained AI models and modern vision systems used in agriculture.
• Gain introductory exposure to model fine-tuning and deployment using PyTorch and Hugging Face.
• Identify research opportunities and innovation challenges in Smart Agriculture.
• Develop technology and research roadmaps for future AgriTech solutions.

Course Content & Class Plan (Modules)

• Module A: IoT for Smart Farming
  
  
• Class 1: Introduction to Smart Farming and IoT Ecosystem (Evolution, precision concepts, architecture, global trends).
• Class 2: Agricultural Sensors and Devices (Soil monitoring, environmental sensors, livestock monitoring, smart irrigation, drones).
• Class 3: Communication Technologies (LoRaWAN, NB-IoT, Zigbee, Wi-Fi, BLE, Cellular).
• Class 4: Device Selection and Deployment Strategy (Comparison, cost analysis, scalability, maintenance, limitations).
• Class 5: Industry Case Studies (Irrigation deployment, greenhouse automation, livestock monitoring, ROI analysis).
• Module B: Computer Vision for Smart Farming
  
  
• Class 6: Introduction to Computer Vision in Agriculture (Fundamentals, use cases, image analytics workflow).
• Class 7: Crop Monitoring Applications (Plant disease detection, pest identification, yield estimation, drone imaging).
• Class 8: Livestock Monitoring Applications (Animal detection, behavior analysis, health monitoring, automated surveillance).
• Class 9: Modern AI Vision Systems (Deep learning, object detection, image segmentation, transfer learning, case studies).
• Class 10: Hands-on Demonstration with PyTorch and Hugging Face (Loading pre-trained models, fine-tuning, FastAPI/Flask pipelines).
• Module C: Research Methodology and Innovation in Smart Farming
  
  
• Class 11 & 12: Research Landscape, Key Challenges, Problem Identification, and Literature Review Techniques.
• Class 13 & 14: Research Design (Experimental, quantitative/qualitative), Data Collection, and Writing/Publication Ethics.
• Class 15: Research Roadmap and Innovation Workshop (Funding, startup pathways, proposal presentations).

Practical & Field Work

• Hands-on Labs: Loading pre-trained Hugging Face Vision Models, executing fine-tuning pipelines on agricultural datasets, and building a simple prediction API using FastAPI or Flask.
• Case Study Analytics: Analyzing commercial AgriTech deployment successes, smart irrigation setups, and automation ecosystems.
• Innovation Workshops: Engaging in interactive mini-research proposal development and technological roadmap planning.

Learning Outcomes

Upon successful completion, learners will be able to:

1. Explain the architecture and applications of IoT-based smart farming systems.
2. Evaluate agricultural sensors, communication technologies, and deployment strategies.
3. Analyze computer vision solutions for agricultural and livestock monitoring.
4. Understand the workflow of modern AI vision systems and transfer learning techniques.
5. Demonstrate a basic understanding of fine-tuning pre-trained models using PyTorch and Hugging Face.
6. Formulate research problems and identify innovation opportunities in AgriTech.
7. Develop practical technology and research roadmaps for smart farming applications.

Target Audience & Requirements

Target Audience:

• Undergraduate and graduate students of CSE, SWE, EEE, and Agriculture disciplines.
• Researchers interested in AI and Smart Agriculture.
• AgriTech entrepreneurs and startup founders.
• Industry and development sector professionals working in agriculture, technology, and sustainability.

Entry Requirements: 

Applicants should satisfy any one of the following criteria:

• Undergraduate student or graduate in CSE, SWE, EEE, Agriculture, or related disciplines.
• Basic understanding of computer applications with an interest in AI, IoT, Agriculture, or Research.
• Note: No prior programming experience is mandatory.
• Minimum Age: 18 years.

Career Pathways

Participants may pursue careers or further studies in:

• AgriTech Solutions Consultant
• Smart Farming Technology Specialist
• IoT Solutions Analyst
• Computer Vision Research Assistant
• Agricultural Data Analyst
• Precision Agriculture Coordinator
• AI and Machine Learning Research Projects
• AgriTech Entrepreneurship

Tools & Resources

• Software Environments: Google Colab, Python, PyTorch, Hugging Face Libraries, FastAPI or Flask, and DIU LMS.
• Learning Resources: Research papers, industry case studies, demonstration datasets, and smart farming videos/reports.
• Hardware: No mandatory hardware requirement.
• Class Size: Maximum 20-30 participants.

Assessment Criteria

Learners must obtain a minimum of 50% overall marks across the following weightage blocks to successfully complete the course:

• Research Proposal Presentation – 40%
  
  
• Module Quizzes – 20%
  
  
• Case Study Analysis – 20%
  
  
• Technology Evaluation Report – 20%
  
  

Financial Information

• Tentative Course Fee: 3,000 BDT.
• Certification: Micro-credential professional certification issued upon successful verification of all criteria.