دورية أكاديمية
A new framework for improving semantic segmentation in aerial imagery
| العنوان: | A new framework for improving semantic segmentation in aerial imagery |
|---|---|
| المؤلفون: | Shuke He, Chen Jin, Lisheng Shu, Xuzhi He, Mingyi Wang, Gang Liu |
| المصدر: | Frontiers in Remote Sensing, Vol 5 (2024) |
| بيانات النشر: | Frontiers Media S.A., 2024. |
| سنة النشر: | 2024 |
| المجموعة: | LCC:Geophysics. Cosmic physics LCC:Meteorology. Climatology |
| مصطلحات موضوعية: | deep learning, aerial imagery, remote sensing segmentation, foreground saliency enhancement, small objects semantic segmentation, Geophysics. Cosmic physics, QC801-809, Meteorology. Climatology, QC851-999 |
| الوصف: | High spatial resolution (HSR) remote sensing imagery presents a rich tapestry of foreground-background intricacies, rendering semantic segmentation in aerial contexts a formidable and vital undertaking. At its core, this challenge revolves around two pivotal questions: 1) Mitigating Background Interference and Enhancing Foreground Clarity. 2) Accurate Segmentation in Dense Small Object Cluster. Conventional semantic segmentation methods primarily cater to the segmentation of large-scale objects in natural scenes, yet they often falter when confronted with aerial imagery’s characteristic traits such as vast background areas, diminutive foreground objects, and densely clustered targets. In response, we propose a novel semantic segmentation framework tailored to overcome these obstacles. To address the first challenge, we leverage PointFlow modules in tandem with the Foreground-Scene (F-S) module. PointFlow modules act as a barrier against extraneous background information, while the F-S module fosters a symbiotic relationship between the scene and foreground, enhancing clarity. For the second challenge, we adopt a dual-branch structure termed disentangled learning, comprising Foreground Precedence Estimation and Small Object Edge Alignment (SOEA). Our foreground saliency guided loss optimally directs the training process by prioritizing foreground examples and challenging background instances. Extensive experimentation on the iSAID and Vaihingen datasets validates the efficacy of our approach. Not only does our method surpass prevailing generic semantic segmentation techniques, but it also outperforms state-of-the-art remote sensing segmentation methods. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2673-6187 |
| Relation: | https://www.frontiersin.org/articles/10.3389/frsen.2024.1370697/full; https://doaj.org/toc/2673-6187 |
| DOI: | 10.3389/frsen.2024.1370697 |
| URL الوصول: | https://doaj.org/article/049d29affb83477e8c0646524343feef |
| رقم الأكسشن: | edsdoj.049d29affb83477e8c0646524343feef |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | تدمد: | 26736187 |
|---|---|
| DOI: | 10.3389/frsen.2024.1370697 |