Method of Building Detection in Optical Remote Sensing Images Based on SegFormer
Sensors · 21.01.2023 · 23 (3) · 1258
DOI: 10.3390/s23031258 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 21.01.2023. Verfasst von Meilin Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Geographic Information, Information Engineering University, Wutong Street High-Tech District, Zhengzhou 450001, China. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
An appropriate detection network is required to extract building information in remote sensing images and to relieve the issue of poor detection effects resulting from the deficiency of detailed features. Firstly, we embed a transposed convolution sampling module fusing multiple normalization activation layers in the decoder based on the SegFormer network. This step alleviates the issue of missing feature semantics by adding holes and fillings, cascading multiple normalizations and activation layers to hold back over-fitting regularization expression and guarantee steady feature parameter classification. Secondly, the atrous spatial pyramid pooling decoding module is fused to explore multi-scale contextual information and to overcome issues such as the loss of detailed information on local buildings and the lack of long-distance information. Ablation experiments and comparison experiments are performed on the remote sensing image AISD, MBD, and WHU dataset. The robustness and validity of the improved mechanism are demonstrated by control groups of ablation experiments. In comparative experiments with the HRnet, PSPNet, U-Net, DeepLabv3+ networks, and the original detection algorithm, the mIoU of the AISD, the MBD, and the WHU dataset is enhanced by 17.68%, 30.44%, and 15.26%, respectively. The results of the experiments show that the method of this paper is superior to comparative methods such as U-Net. Furthermore, it is better for integrity detection of building edges and reduces the number of missing and false detections.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Geographic Information, Information Engineering University, Wutong Street High-Tech District, Zhengzhou 450001, China.
- School of Computer Science & Technology, Beijing Institute of Technology, Haidian District, Beijing 100081, China.
ORCID-Profile: Meilin Li, Xibing Zuo
Zitieren
APA
Li, M., Rui, J., Yang, S., Liu, Z., Ren, L., Ma, L., Li, Q., Su, X., & Zuo, X. (2023). Method of Building Detection in Optical Remote Sensing Images Based on SegFormer. Sensors, 23(3), 1258. https://doi.org/10.3390/s23031258
Vancouver
Li M, Rui J, Yang S, Liu Z, Ren L, Ma L, et al. Method of Building Detection in Optical Remote Sensing Images Based on SegFormer. Sensors. 2023;23(3):1258. doi:10.3390/s23031258
BibTeX
@article{Li2023,
author = {Li, Meilin and Rui, Jie and Yang, Songkun and Liu, Zhi and Ren, Liqiu and Ma, Li and Li, Qing and Su, Xu and Zuo, Xibing},
title = {Method of Building Detection in Optical Remote Sensing Images Based on SegFormer},
journal = {Sensors},
year = {2023},
volume = {23},
number = {3},
pages = {1258},
doi = {10.3390/s23031258}
}
EUVIMED