Build with Azure OpenAI, Copilot Studio & Agentic Frameworks — Microsoft Certified
Live Online Classes in Design, Coding & AI — Small Classes, Free Retakes
Overview
Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Learn how to implement computer vision on live video feeds using Roboflow's Serverless Streaming API and WebRTC technology. Explore the trade-offs between edge hardware deployment (low latency, high maintenance) and dedicated cloud servers (difficult scaling for burst traffic) before discovering how the serverless approach solves these challenges through auto-scaling video inference in the cloud. Master the integration of live vision capabilities into web and mobile applications using Python and JavaScript SDKs with minimal code requirements. Follow along with practical demonstrations including webcam object counting, RTSP stream processing, and mobile iOS exercise tracking applications. Understand the underlying WebRTC architecture that enables direct video streaming to cloud-based custom models and workflows for real-time processing. Compare different Roboflow cloud deployment options including serverless, dedicated, and batch processing to determine the optimal solution for your computer vision projects.
Syllabus
- Intro: Computer Vision on Live Video
- Choosing Infrastructure: Edge vs. Cloud
- Roboflow Cloud Options Serverless vs. Dedicated vs. Batch
- Introducing the Serverless Streaming API
- How it Works: WebRTC & Architecture
- Demo 1: JavaScript SDK & Webcam Object Counting
- Demo 2: Python SDK with RTSP Streams
- Demo 3: Mobile App iOS Squat Counter
Taught by
Roboflow