Single image smoke detection

Authors

Hongda Tian, University of WollongongFollow
Wanqing Li, University of WollongongFollow
Philip Ogunbona, University of WollongongFollow
Lei Wang, University of WollongongFollow

RIS ID

103917

Publication Details

Tian, H., Li, W., Ogunbona, P. & Wang, L. (2015). Single image smoke detection. In D. Cremers, I. Reid, H. Saito & M. Yang (Eds.), Lecture Notes in Computer Science: Computer Vision - ACCV 2014: 12th Asian Conference on Computer Vision Singapore (pp. 87-101). Switzerland: Springer.

Abstract

Despite the recent advances in smoke detection from video, detection of smoke from single images is still a challenging problem with both practical and theoretical implications. However, there is hardly any reported research on this topic in the literature. This paper addresses this problem by proposing a novel feature to detect smoke in a single image. An image formation model that expresses an image as a linear combination of smoke and non-smoke (background) components is derived based on the atmospheric scattering models. The separation of the smoke and non-smoke components is formulated as convex optimization that solves a sparse representation problem. Using the separated quasi-smoke and quasi-background components, the feature is constructed as a concatenation of the respective sparse coefficients. Extensive experiments were conducted and the results have shown that the proposed feature significantly outperforms the existing features for smoke detection.