期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 59, 期 9, 页码 7918-7932出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3044655
关键词
Feature extraction; Semantics; Spatial resolution; Convolution; Remote sensing; Deconvolution; Task analysis; Convolutional neural network (CNN); deep semantic embedding (DSE); feature pyramid network (FPN); remote sensing (RS) image; scene classification
类别
资金
- Fundamental Research Funds for the Central Universities [B210202077]
- Six Talents Peak Project of Jiangsu Province [XYDXX-007]
- Jiangsu Province Government Scholarship for Studying Abroad
- Royal Society-Newton Advanced Fellowship [NA160342]
- European Union's Horizon 2020 Research and Innovation Program through the Marie-Sklodowska-Curie [720325]
This article proposes a novel RS scene classification method using EFPN and DSE to extract features, and introduces a TDFF module for feature fusion, achieving state-of-the-art results better than existing algorithms.
Recent progress on remote sensing (RS) scene classification is substantial, benefiting mostly from the explosive development of convolutional neural networks (CNNs). However, different from the natural images in which the objects occupy most of the space, objects in RS images are usually small and separated. Therefore, there is still a large room for improvement of the vanilla CNNs that extract global image-level features for RS scene classification, ignoring local object-level features. In this article, we propose a novel RS scene classification method via enhanced feature pyramid network (EFPN) with deep semantic embedding (DSE). Our proposed framework extracts multiscale multilevel features using an EFPN. Then, to leverage the complementary advantages of the multilevel and multiscale features, we design a DSE module to generate discriminative features. Third, a feature fusion module, called two-branch deep feature fusion (TDFF), is introduced to aggregate the features at different levels in an effective way. Our method produces state-of-the-art results on two widely used RS scene classification benchmarks, with better effectiveness and accuracy than the existing algorithms. Beyond that, we conduct an exhaustive analysis on the role of each module in the proposed architecture, and the experimental results further verify the merits of the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据