Video Smoke Detection Based on Deep Saliency Network

TL;DR

This paper introduces a novel deep saliency network-based method for video smoke detection, effectively highlighting smoke regions and predicting smoke presence in videos, especially useful in outdoor environments.

Contribution

The paper proposes an end-to-end deep saliency network framework combining pixel-level and object-level saliency for improved smoke detection in videos, which is a novel approach.

Findings

High accuracy in smoke region localization

Effective smoke existence prediction in videos

Superior performance over traditional methods

Abstract

Video smoke detection is a promising fire detection method especially in open or large spaces and outdoor environments. Traditional video smoke detection methods usually consist of candidate region extraction and classification, but lack powerful characterization for smoke. In this paper, we propose a novel video smoke detection method based on deep saliency network. Visual saliency detection aims to highlight the most important object regions in an image. The pixel-level and object-level salient convolutional neural networks are combined to extract the informative smoke saliency map. An end-to-end framework for salient smoke detection and existence prediction of smoke is proposed for application in video smoke detection. The deep feature map is combined with the saliency map to predict the existence of smoke in an image. Initial and augmented dataset are built to measure the performance of frameworks with different design strategies. Qualitative and quantitative analysis at frame-level and pixel-level demonstrate the excellent performance of the ultimate framework.