Learning to Upsample Smoke Images via a Deep Convolutional Network

Abstract

The flare, which aims to burn all kinds of waste gas produced by petrochemical enterprises, is an important facility for plants to keep safe and prevent harming the environment. However, when the exhaust gas is not sufficiently burned, black smoke will be produced in the flare system and endanger air quality and human health. So, as a crucial task, reducing the emission of flare black smoke is attracting a growing amount of research attention. In a typical flare smoke reduction system, a high-resolution smoke image is greatly beneficial to smoke recognition and analysis. But the smoke image usually encounters the low-resolution problem. Accordingly, in this paper we propose a super-resolution method specific for smoke images, which is called smoke images upsampling method (SIUM). Considering the texture and edge characteristics of the smoke images, the proposed SIUM learns a mapping between the low-resolution images and the associated high-resolution images. Experimental results demonstrate that our proposed SIUM is prominently superior to relevant state-of-the-art technologies when applied to upsample low-resolution smoke images.

Keywords

• Smoke images
• air pollution
• upsampling
• deep convolutional network