SaNet: Scale-aware neural Network for Parsing Multiple Spatial Resolution Aerial Images.
Year: 2021
Type: preprint
Abstract: Assigning the geospatial objects of aerial images with categorical information at the pixel-level is a basic task in urban scene understanding. However, the huge differencc in remote sensing sensors makes the acqured aerial images in multiple spatial resolution (MSR), which brings two issues: the increased scale variation of geospatial objects and informative feature loss as spatial resolution drops. To address the two issues, we propose a novel scale-aware neural network (SaNet) for parsing MSR aerial images. For coping with the imbalanced segmentation quality between larger and smaller objects caused by the scale variation, the SaNet deploys a densely connected feature network (DCFPN) module to capture quality multi-scale context with large receptive fields. To alleviate the informative feature loss, a SFR module is incorporated into the network to learn scale-invariant features with spatial relation enhancement. Extensive experimental results on the ISPRS Vaihingen 2D Dataset and ISPRS Potsdam 2D Dataset demonstrate the outstanding cross-resolution segmentation ability of the proposed SaNet compared to other state-of-the-art networks.
Source: arXiv (Cornell University)
Author: Libo Wang
Institution: Wuhan University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3136978210