Multiple Categories Of Visual Smoke Detection Database

Abstract

Smoke detection has become a significant task in associated industries due to the close relationship between the petrochemical industry's smoke emission and its safety production and environmental damage. There are several production situations in the real industrial production environment, including complete combustion of exhaust gas, inadequate combustion of exhaust gas, direct emission of exhaust gas, etc. We discovered that the datasets used in previous research work could only determine whether smoke is present or not, not its type. That is, the dataset's category does not map to real-world production situations, which are not conducive to the precise regulation of the production system. In order to reduce the gap between the algorithm and the actual application so that the new algorithm can more comprehensively cover and solve the actual situations, we created a multi-categories smoke detection database that in-cludes a total of 70196 images. We further conduct the experiment by employing multiple models on the proposed database. The results demonstrate the effectiveness of the proposed database and show that the performance of the current algorithms needs to be improved.