Upsampling Flare Soot Pictures by Fusing Global Perception and Local Details

Abstract

The flare stack is a flare gas combustion facility used to ensure the safe production of petrochemical enterprises. However, in petrochemical enterprises, cameras are far away from the flare stacks, which causes the collected flare soot pictures to be too blurry to be analyzed further. To that end, we devise an Upsampling Flare Soot Pictures Director (UFSPD) based on the global perception and local details. First, we get the global perception map and the local details map of a low resolution flare soot picture via guided filtering and edge extraction, respectively. Then, the upsampling method is used to upsample the above two maps to get the corresponding high-resolution picture. Finally, the two pictures in the second step are fused at the pixel-level to get a satisfactory flare soot picture. Experiments show that the proposed UFSPD model is more competitive than other state-of-the-art models in some image quality evaluation indexes, and it also helps to improve the detection rate of flare soot.