A2-FPN for semantic segmentation of fine-resolution remotely sensed images

Li, Rui; Wang, Libo; Zhang, Ce ORCID: https://orcid.org/0000-0001-5100-3584; Duan, Chenxi; Zheng, Shunyi. 2022 A2-FPN for semantic segmentation of fine-resolution remotely sensed images. International Journal of Remote Sensing, 43 (3). 1131-1155. https://doi.org/10.1080/01431161.2022.2030071

Before downloading, please read NORA policies.

Preview

Text N532410JA.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0. Download (17MB) | Preview

Abstract/Summary

The thriving development of earth observation technology makes more and more high-resolution remote-sensing images easy to obtain. However, caused by fine-resolution, the huge spatial and spectral complexity leads to the automation of semantic segmentation becoming a challenging task. Addressing such an issue represents an exciting research field, which paves the way for scene-level landscape pattern analysis and decision-making. To tackle this problem, we propose an approach for automatic land segmentation based on the Feature Pyramid Network (FPN). As a classic architecture, FPN can build a feature pyramid with high-level semantics throughout. However, intrinsic defects in feature extraction and fusion hinder FPN from further aggregating more discriminative features. Hence, we propose an Attention Aggregation Module (AAM) to enhance multiscale feature learning through attention-guided feature aggregation. Based on FPN and AAM, a novel framework named Attention Aggregation Feature Pyramid Network (A2-FPN) is developed for semantic segmentation of fine-resolution remotely sensed images. Extensive experiments conducted on four datasets demonstrate the effectiveness of our A2-FPN in segmentation accuracy. Code is available at https://github.com/lironui/A2-FPN.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	https://doi.org/10.1080/01431161.2022.2030071
UKCEH and CEH Sections/Science Areas:	Soils and Land Use (Science Area 2017-)
ISSN:	0143-1161
Additional Information. Not used in RCUK Gateway to Research.:	Open Access paper - full text available via Official URL link.
Additional Keywords:	semantic segmentation, deep learning, attention mechanism
NORA Subject Terms:	Electronics, Engineering and Technology Computer Science Data and Information
Date made live:	05 Apr 2022 11:44 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/532410

Actions (login required)

View Item

Document Downloads

More statistics for this item...