Transmission-Guided Bayesian Generative Model for Smoke Segmentation

TL;DR

This paper introduces a Bayesian generative model for smoke segmentation that effectively captures uncertainty, guided by transmission-based local coherence, and is validated on a new high-quality dataset, SMOKE5K.

Contribution

It proposes a novel Bayesian generative approach for smoke segmentation that models uncertainty and incorporates transmission-guided loss, along with a new dataset for benchmarking.

Findings

Achieves accurate smoke segmentation with reliable uncertainty estimation.

Outperforms existing methods on benchmark datasets.

Provides a new high-quality dataset, SMOKE5K.

Abstract

Smoke segmentation is essential to precisely localize wildfire so that it can be extinguished in an early phase. Although deep neural networks have achieved promising results on image segmentation tasks, they are prone to be overconfident for smoke segmentation due to its non-rigid shape and transparent appearance. This is caused by both knowledge level uncertainty due to limited training data for accurate smoke segmentation and labeling level uncertainty representing the difficulty in labeling ground-truth. To effectively model the two types of uncertainty, we introduce a Bayesian generative model to simultaneously estimate the posterior distribution of model parameters and its predictions. Further, smoke images suffer from low contrast and ambiguity, inspired by physics-based image dehazing methods, we design a transmission-guided local coherence loss to guide the network to learn pair-wise relationships based on pixel distance and the transmission feature. To promote the development of this field, we also contribute a high-quality smoke segmentation dataset, SMOKE5K, consisting of 1,400 real and 4,000 synthetic images with pixel-wise annotation. Experimental results on benchmark testing datasets illustrate that our model achieves both accurate predictions and reliable uncertainty maps representing model ignorance about its prediction. Our code and dataset are publicly available at: https://github.com/redlessme/Transmission-BVM.