Year: 2020
Type: preprint
Abstract: High-resolution images for remote sensing applications are often not affordable or accessible, especially when in need of a wide temporal span of recordings. Given the easy access to low-resolution (LR) images from satellites, many remote sensing works rely on this type of data. The problem is that LR images are not appropriate for semantic segmentation, due to the need for high-quality data for accurate pixel prediction for this task. In this paper, we propose an end-to-end framework that unites a super-resolution and a semantic segmentation module in order to produce accurate thematic maps from LR inputs. It allows the semantic segmentation network to conduct the reconstruction process, modifying the input image with helpful textures. We evaluate the framework with three remote sensing datasets. The results show that the framework is capable of achieving a semantic segmentation performance close to native high-resolution data, while also surpassing the performance of a network trained with LR inputs.
Source: arXiv (Cornell University)
Authors: Pereira, Matheus Barros, Santos, Jefersson Alex dos
Institution: Universidade Federal de Minas Gerais
Language: English
Subfield: Media Technology
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4287826023