Through-Foliage Surface-Temperature Reconstruction for early Wildfire Detection

2025-11-16

AI Summary

Forest canopy occlusion impedes ground temperature observation, hindering early autonomous wildfire detection. Method: This paper proposes a novel framework integrating synthetic aperture thermal imaging, visual state-space modeling, and latent diffusion generation. A high-fidelity synthetic dataset is constructed via procedural forest thermal simulation and temperature augmentation, enabling the first high-accuracy morphological reconstruction of occluded fire sources and human thermal signatures. Vector quantization is incorporated to enhance generation efficiency and physical consistency. Contribution/Results: In both simulated and field experiments, the method achieves a 2×–12.8× reduction in RMSE over conventional thermal imaging, significantly improving high-temperature hotspot detection accuracy and thermal source structural fidelity. It establishes a robust perception foundation for pre-smoke wildfire warning during autonomous UAV patrols.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

We introduce a novel method for reconstructing surface temperatures through occluding forest vegetation by combining signal processing and machine learning. Our goal is to enable fully automated aerial wildfire monitoring using autonomous drones, allowing for the early detection of ground fires before smoke or flames are visible. While synthetic aperture (SA) sensing mitigates occlusion from the canopy and sunlight, it introduces thermal blur that obscures the actual surface temperatures. To address this, we train a visual state space model to recover the subtle thermal signals of partially occluded soil and fire hotspots from this blurred data. A key challenge was the scarcity of real-world training data. We overcome this by integrating a latent diffusion model into a vector quantized to generated a large volume of realistic surface temperature simulations from real wildfire recordings, which we further expanded through temperature augmentation and procedural thermal forest simulation. On simulated data across varied ambient and surface temperatures, forest densities, and sunlight conditions, our method reduced the RMSE by a factor of 2 to 2.5 compared to conventional thermal and uncorrected SA imaging. In field experiments focused on high-temperature hotspots, the improvement was even more significant, with a 12.8-fold RMSE gain over conventional thermal and a 2.6-fold gain over uncorrected SA images. We also demonstrate our model's generalization to other thermal signals, such as human signatures for search and rescue. Since simple thresholding is frequently inadequate for detecting subtle thermal signals, the morphological characteristics are equally essential for accurate classification. Our experiments demonstrated another clear advantage: we reconstructed the complete morphology of fire and human signatures, whereas conventional imaging is defeated by partial occlusion.

Problem

• Reconstructing surface temperatures through forest vegetation for early wildfire detection
• Overcoming thermal blur in synthetic aperture sensing that obscures actual temperatures
• Addressing scarcity of real-world training data for thermal signal recovery

Innovation

• Combining signal processing with machine learning
• Training visual state space model for thermal recovery
• Using latent diffusion model for data generation