FireWarn: Fire Hazards Detection Using Deep Learning Models
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
Hazardous situations such as house, car, or forest fires may be recorded by cameras long before they are identified by people. To test whether deep learning could be used to quickly detect fires, we performed a series of experiments to detect the presence of fire or smoke in images and labeled them with bounding boxes. Two custom datasets were created in this research: a fire image classification dataset, and a fire and smoke detection and localization dataset. The first one only classifies the whole image, while the detection set further provides information about where the fire or smoke is within the image. We explore the efficacy of a basic convolutional classification neural network, which proved effective for fire classification, but show that pretrained classification models such as ResNet improves the accuracy when classifying fire and non-fire images. The pretrained model achieves 97.14% testing accuracy on our fire classification dataset. For fire detection and localization, three models were trained on images of fire and smoke to find and label the regions of interest. Results show that Faster R-CNN did not perform very well on fire detection and localization, while EfficientDet and YoloV5 performed much better. Moreover, YoloV5 using low resolution images also performed well on smoke detection and localization, which is more difficult than fire. YoloV5 achieved an average precision of 46.6 on our fire and smoke detection dataset.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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