Wildfire is a common and important natural phenomenon in the biosphere, being a critical link between vegetation succession on the land surface and the terrestrial carbon cycle (Abatzoglou et al., 2018;Thevenon et al., 2010). The occurrence of wildfire results in the transformation of forest and grassland from a carbon sink to a carbon source, with effects on the carbon dioxide content of the atmosphere and on the cycling of materials in terrestrial ecosystems (Han et al., 2020;Marlon et al., 2013). The products of combustion are the most direct evidence of wildfire; for example, black carbon (BC) is a chemically inert, micron-or submicron-sized spherical material with high thermal stability and a highly condensed aromatic hydrocarbon structure, which is produced by the incomplete combustion of biomass or fossil fuels (Bond et al.
We designed an end-to-end dual-branch residual network architecture that inputs a low-resolution (LR) depth map and a corresponding high-resolution (HR) color image separately into the two branches, and outputs an HR depth map through a multi-scale, channel-wise feature extraction, interaction, and upsampling. Each branch of this network contains several residual levels at different scales, and each level comprises multiple residual groups composed of several residual blocks. A short-skip connection in every residual block and a long-skip connection in each residual group or level allow for low-frequency information to be bypassed while the main network focuses on learning high-frequency information. High-frequency information learned by each residual block in the color image branch is input into the corresponding residual block in the depth map branch, and this kind of channel-wise feature supplement and fusion can not only help the depth map branch to alleviate blur in details like edges, but also introduce some depth artifacts to feature maps. To avoid the above introduced artifacts, the channel interaction fuses the feature maps using weights referring to the channel attention mechanism. The parallel multi-scale network architecture with channel interaction for feature guidance is the main contribution of our work and experiments show that our proposed method had a better performance in terms of accuracy compared with other methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.