AusSmoke meets MultiNatSmoke: a fully-labelled diverse smoke segmentation dataset

2026-04-26

AI Summary

Existing wildfire smoke segmentation datasets are limited in scale, geographically narrow, and often rely on synthetic imagery, which constrains model training and generalization. To address these limitations, this work introduces AusSmoke, the first real-world smoke dataset based on Australian scenes, and integrates it with publicly available multi-national data to construct MultiNatSmoke—the largest and most geographically diverse fully pixel-annotated benchmark for smoke segmentation to date. This new benchmark increases data volume by an order of magnitude and, through systematic experiments, demonstrates substantial improvements in both performance and cross-regional generalization of smoke segmentation models.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Wildfires are an escalating global concern due to the devastating impacts on the environment, economy, and human health, with notable incidents such as the 2019-2020 Australian bushfires and the 2025 California wildfires underscoring the severity of these events. AI-enabled camera-based smoke detection has emerged as a promising approach for the rapid detection of wildfires. However, existing wildfire smoke segmentation datasets that are used for training detection and segmentation models are limited in scale, geographically constrained, and often rely on synthetic imagery, which hinders effective training and generalization. To overcome these limitations, we present AusSmoke, a new smoke segmentation dataset collected from Australia to address the data scarcity in this region. Furthermore, we introduce a MultiNational geographically diverse and substantially larger fully-labelled benchmark, called MultiNatSmoke, that consolidates publicly available international datasets with the newly collected Australian imagery, expanding the scale by an order of magnitude over previous collections. Finally, we benchmark smoke segmentation models, demonstrating improved performance and enhanced generalization across diverse geographical contexts. The project is available at \href{https://github.com/henryzhao0615/MultiNatSmoke}{Github}.

Problem

• wildfire smoke segmentation
• dataset scarcity
• geographical diversity
• synthetic imagery
• model generalization

Innovation

• smoke segmentation
• wildfire detection
• geographically diverse dataset
• fully-labelled benchmark
• MultiNatSmoke