Multitask Semantic Boundary Awareness Network for Remote Sensing Image Segmentation
العنوان: | Multitask Semantic Boundary Awareness Network for Remote Sensing Image Segmentation |
---|---|
المؤلفون: | Fang Liu, Licheng Jiao, Lingling Li, Hao Zhu, Aijin Li |
المصدر: | IEEE Transactions on Geoscience and Remote Sensing. 60:1-14 |
بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2022. |
سنة النشر: | 2022 |
مصطلحات موضوعية: | Computer science, Feature extraction, 0211 other engineering and technologies, Multi-task learning, Boundary (topology), 02 engineering and technology, computer.software_genre, Key (cryptography), General Earth and Planetary Sciences, Segmentation, Data mining, Noise (video), Remote sensing image segmentation, Electrical and Electronic Engineering, Semantic information, computer, 021101 geological & geomatics engineering |
الوصف: | In remote sensing images, boundary information plays a crucial role in land-cover segmentation. However, it is a challenging problem that sufficiently extracts complete and sharp boundaries from complex very-high-resolution (VHR) remote sensing images. To tackle this problem, we propose a semantic boundary awareness network (SBANet). The SBANet captures refined boundary information of land covers in feature extraction and then supervises its learning with a designed boundary loss. The key of SBANet includes boundary attention module (BA-module) and adaptive weights of multitask learning (AWML). The BA-module is proposed to capture land-cover boundary information from hierarchical features aggregation in a bottom-up manner. It emphasizes useful boundary information and relieves noise information in low-level features with the guidance of high-level features. To directly learn the boundary information, AWML adds a boundary loss to the original semantic loss by an adaptive fusion manner. This multitask learning enables the semantic information and the boundary information to work collaboratively and promote each other. Note that the BA-module and AWML are plug-and-play. Experimental results demonstrate the effectiveness of the proposed SBANet on the available ISPRS 2-D semantic labeling Potsdam and Vaihingen data sets. The SBANet also achieves the state-of-the-art performance in terms of overall accuracy (OA) and mean F₁ score (m-F₁). |
تدمد: | 1558-0644 0196-2892 |
URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::cf4461ebacee1db80ce776191384e68b https://doi.org/10.1109/tgrs.2021.3050885 |
حقوق: | CLOSED |
رقم الأكسشن: | edsair.doi...........cf4461ebacee1db80ce776191384e68b |
قاعدة البيانات: | OpenAIRE |
تدمد: | 15580644 01962892 |
---|