Reproduce “Edge Computing for Computer Vision in IoT: Feasibility and Directions” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Panagiotis Savvidis, George A. Papakostas
The authors assess small edge boards and low-power links for remote image analysis. They test YOLOv4 apple detection on a modest dataset, compare inference on a Jetson Nano and Raspberry Pi 4B, and separately evaluate LoRaWAN and receive-only satellite reception. At 608×608, Jetson inference takes 29.93 seconds versus 91.29 seconds on the Pi; the findings establish feasibility, not an integrated deployment or cloud advantage.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.