Spatio-Temporal Flame Modeling and Dynamic Texture Analysis for Automatic Video-Based Fire Detection

TLDR

Wildfires worldwide inflict significant ecological, economic, and social damage, making early warning and rapid response essential to mitigate losses. This study introduces a computer‑vision based fire‑flame detection method intended for integration into an early‑warning fire monitoring system. The approach first isolates candidate fire regions via background subtraction and nonparametric color modeling, then extracts spatio‑temporal features—including color probability, flickering, spatial and spatio‑temporal energy—and applies dynamic texture analysis with linear dynamical systems and a bag‑of‑systems representation, refines candidates using spatio‑temporal consistency across neighboring blocks, and finally classifies them with a two‑class support vector machine. Experiments demonstrate that the proposed method surpasses existing state‑of‑the‑art algorithms in fire detection performance.

Abstract

Every year, a large number of wildfires all over the world burn forested lands, causing adverse ecological, economic, and social impacts. Beyond taking precautionary measures, early warning and immediate response are the only ways to avoid great losses. To this end, in this paper we propose a computer vision approach for fire-flame detection to be used by an early-warning fire monitoring system. Initially, candidate fire regions in a frame are defined using background subtraction and color analysis based on a nonparametric model. Subsequently, the fire behavior is modeled by employing various spatio-temporal features, such as color probability, flickering, spatial, and spatio-temporal energy, while dynamic texture analysis is applied in each candidate region using linear dynamical systems and a bag-of-systems approach. To increase the robustness of the algorithm, the spatio-temporal consistency energy of each candidate fire region is estimated by exploiting prior knowledge about the possible existence of fire in neighboring blocks from the current and previous video frames. As a final step, a two-class support vector machine classifier is used to classify the candidate regions. Experimental results have shown that the proposed method outperforms existing state-of-the-art algorithms.