CCTV setups are everywhere, providing live video feeds 24/7. However, most systems only capture video—they don’t truly understand what’s happening in it. Building a computer vision system that interprets video content can enable real-time alerts and actionable insights.
Nvidia’s DeepStream, built on top of GStreamer, is a flagship software which can process multiple camera streams in real time and run deep learning models on each stream in parallel. Optimized for Nvidia GPUs using TensorRT, it’s a powerful tool for developing video analytics applications.
In this hands-on online workshop, you will learn:
This is a live, hands-on workshop where you can follow along, apply what you learn immediately, and build practical skills. There will also be a live Q&A session, so participants can ask questions and clarify doubts right then and there!
Prerequisites:
System Requirements:
Ubuntu 22.04 with Nvidia GPU (optional)
All skill levels are welcome! Participants will receive an e-certificate upon completion of the workshop.
Arun Ponnusamy holds a Bachelor’s degree in Electronics and Communication Engineering from PSG College of Technology, Coimbatore. With a decade of experience as a Computer Vision Engineer in various AI startups, he has specialized in areas such as image classification, object detection, object tracking, human activity detection, and face recognition. As the founder of Vision Geek, an AI education startup, and the creator of the open-source Python library “cvlib,” Arun is committed to making computer vision and machine learning accessible to all. He has led workshops at institutions like VIT and IIT and spoken at various community events, always aiming to simplify complex concepts.
LinkedIn: linkedin.com/in/arun-ponnusamy