Early Wildfire Smoke Detection with a Multi-Resolution Framework and Two-Stage Classification Pipeline
Open Access
Abstract
Early wildfire smoke detection is critical for preventing small ignitions from escalating into large-scale fires, yet early-stage smoke plumes are often faint, low-contrast, and spatially small. When full-resolution frames are resized to satisfy fixed-input detector architectures and enable efficient batched GPU inference, these subtle cues are further diminished, leading to missed detections and unreliable scores near deployment thresholds. Existing remedies such as multi-scale inference, slicing/tiling, or super-resolution could improve sensitivity, but typically incur substantial overhead from multiple forward passes or added network components, limiting real-time use on resource-constrained platforms. To mitigate these challenges, we propose a composite multi-resolution detection framework that improves sensitivity to small smoke regions while maintaining single-pass inference. Motivated by the fact that most operational wildfire monitoring systems rely on Unmanned Aerial Vehicle (UAV) platforms and mountain-top Closed-Circuit Television (CCTV) systems surveillance, their wide-field imagery typically contains a large sky region above the horizon where early smoke is most likely to first become visible. Accordingly, crop placement is guided by a skyline prior that prioritizes this high-probability sky band while retaining the remaining scene for global context. A dynamic compositing stage stacks a global view with a high-resolution, sky-aligned band into a standard square detector input, preserving context with minimal added cost. Detections from the two views are reconciled via coordinate restoration and non-maximum suppression. For deployment, a lightweight second-stage classifier selectively re-evaluates low-confidence detections to stabilize decisions near a fixed operating threshold without retraining the detector. Compared to the baseline detector, our approach improves detection performance on the Early Smoke dataset, achieving gains of +4.6 percentage points in AP @0.5:0.95, +3.4 percentage points in AP @0.5, +2.9 percentage points in precision, +5.3 percentage points in recall, and +4.3 percentage points in F1-score.Keywords
All Related Versions
Funding Information
- Ministry of Education (MOE) and the 758 Seoul Metropolitan Government (2025-RISE-01-019-04)
- National Science Foundation (2430236)
This publication has 48 references indexed in Scilit:
- Enhancing Tiny Object Detection Using Guided Object Inference Slicing (GOIS): An efficient dynamic adaptive framework for fine-tuned and non-fine-tuned deep learning modelsNeurocomputing, 2025
- A comprehensive survey of research towards AI-enabled unmanned aerial systems in pre-, active-, and post-wildfire managementInformation Fusion, 2024
- Computer vision for wildfire detection: a critical brief reviewMultimedia Tools and Applications, 2024
- SegNet: A segmented deep learning based Convolutional Neural Network approach for drones wildfire detectionRemote Sensing Applications: Society and Environment, 2024
- Development of early fire detection model for buildings using computer vision-based CCTVJournal of Building Engineering, 2022
- A combined real-time intelligent fire detection and forecasting approach through cameras based on computer vision methodProcess Safety and Environmental Protection, 2022
- Focus-and-Detect: A small object detection framework for aerial imagesSignal Processing: Image Communication, 2022
- Remote sensing image super-resolution and object detection: Benchmark and state of the artExpert Systems with Applications, 2022
- Real-time wildfire monitoring with a fleet of UAVsRobotics and Autonomous Systems, 2022
- Smoke detection in video using wavelets and support vector machinesFire Safety Journal, 2009