Reproduce “Image-Based Fire Detection in Industrial Environments with YOLOv4” 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
Otto Zell, Joel Pålsson, Kevin Hernandez-Diaz, Fernando Alonso-Fernandez, Felix Nilsson
The authors evaluate a camera-based YOLOv4 system that detects fire and smoke in successive images, alongside conventional ceiling alarms in a staged warehouse-fire video. Models trained on manually labeled images reached 99.3% precision for image-level fire recognition and 82.3% average precision for fire detection. In one video, camera warnings preceded alarms by 12 and 23 seconds, not establishing general reliability.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.