EdgeFlame: A Physics-Inspired Framework for Zero-Shot Fire and Smoke Recognition
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Wildfires and smoke pose serious threats that demand rapid and reliable detection, especially on autonomous platforms operating under limited resources. We present EdgeFlame, a physics-inspired cross-modal learning framework for zero-shot fire and smoke classification on drones and IoT devices. It combines 3D CWT features with a Stationary Action Principle–guided architecture to link physical signal dynamics with lightweight AI inference. The model is highly efficient, requiring only 0.12 MB of parameters and achieving 3,281 frames per second with a latency of just 0.30 milliseconds. It outperforms conventional baselines such as CLIP, YOLOv12, and ResNet50 in both speed and efficiency. Tested on three diverse datasets—Kaggle Fire, YouTube wildfire videos, and the RGBIR FLAME2 drone dataset—EdgeFlame consistently achieves 94–98% accuracy across different environments. Designed for onboard edge deployment, it enables real-time wildfire perception on autonomous UAVs without relying on large-scale retraining, offering a practical and scalable solution for disaster response robotics.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it