AI-Driven Video Analytics for Smart Surveillance

About Course
This project is structured to help you learn how to develop a smart surveillance system that leverages object detection models (YOLO), integrated with a simple user interface built with Streamlit. The goal is to teach core skills and provide hands-on experience in computer vision, deep learning, and cloud deployment using AWS.
This is a hands-on project and not a course on computer vision and deep learning. For understanding fundamental concepts in computer vision, we provide various external links within the project that you can check out during the timeline of the project. We provide brief explanation of the code given but we encourage the students to read more about OpenCV, YOLO and AWS from official documents.
Project Overview:
- Duration: 10 weeks
- Tech Stack: Python (OpenCV, YOLO, TensorFlow), Streamlit, AWS (SageMaker, Lambda, S3), Docker
- Objective: Build a smart video surveillance system that can detect objects, identify anomalies, and send real-time alerts for potential security threats. The system will leverage object detection models (YOLO) and deploy it in AWS.
- Skills Acquired: Computer vision (YOLO, OpenCV), real-time video processing, deep learning, cloud-based AI services.
- Difficulty: Intermediate to Expert
Course Content
Week 1-2: Environment Setup and Computer Vision Basics
-
Development Environment Setup
-
Basic Image and Video Processing with OpenCV
-
Quiz 1
Week 3-4: Object Detection using YOLO
Week 5-6: Creating the User Interface with Streamlit
Week 7-8: Deploying the Model on AWS
Week 9-10: Anomaly Detection and Real-Time Alerts
Student Ratings & Reviews
No Review Yet