A Novel Impervious Surface Extraction Method Based on Transformer

Wenjing Zhang, Dehui Qiu*, Xiaohua Wan*, Fa Zhang, Huimei Yuan

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

The amount of impervious surface is an important indicator to measure the degree of urbanization and the urban ecological environment. However, the objects in the low-density impervious surface areas are small and scattered, which are easily confused with the background. Therefore, the extraction of the small and scattered impervious surfaces is still challenging. In this study, we propose a dual-branch network combing transformer and CNN with attention mechanism. In this model, transformer branch is first used to extract impervious surface to capture long-distance and large-scale dependencies. In addition, another UNet branch embedded the coordinate attention mechanism can capture detailed information and meanwhile reduce information redundancy. Experiments show that our proposed method performs better than the traditional CNN methods.

源语言英语
主期刊名IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
6851-6854
页数4
ISBN(电子版)9798350320107
DOI
出版状态已出版 - 2023
活动2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, 美国
期限: 16 7月 202321 7月 2023

出版系列

姓名International Geoscience and Remote Sensing Symposium (IGARSS)
2023-July

会议

会议2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
国家/地区美国
Pasadena
时期16/07/2321/07/23

指纹

探究 'A Novel Impervious Surface Extraction Method Based on Transformer' 的科研主题。它们共同构成独一无二的指纹。

引用此