Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore a cutting-edge conference talk on near-realtime Earth observation using satellite imagery. Dive into the innovative Serval system, designed to overcome networking bottlenecks and enable rapid insights for latency-sensitive applications like forest fire detection and disaster monitoring. Learn how researchers from the University of Illinois Urbana-Champaign leverage predictable satellite orbits and bifurcate computation between satellites and ground stations to dramatically reduce end-to-end latency. Discover the challenges of limited computational capabilities and power resources on satellites, and how Serval addresses these issues. Gain insights into the evaluation process using trace-driven simulations and hardware emulations on a massive dataset of ten million images from the Planet Dove constellation. Understand how Serval significantly improves response times for high-priority queries, reducing latency from over 70 hours to just minutes.
