Remote Sensing Image Scene Classification: Benchmark and State of the Art
Remote Sensing Image Scene Classification: Benchmark and State of the Art
复制标题
遥感图像场景分类：基准和最新技术
DOI：
10.1109/jproc.2017.2675998
复制
发表时间：
2017-10-01
影响因子：
20.6
通讯作者：
Lu, Xiaoqiang
中科院分区：
文献类型：
--
作者：
Cheng, Gong;Han, Junwei;Lu, Xiaoqiang
遥感图像场景分类具有重要的应用价值，因此受到了广泛的关注。在过去的几年中，已经作出了重大努力，开发各种数据集或提出了各种方法，从遥感图像的场景分类。然而，一个系统的文献回顾有关的数据集和场景分类的方法仍然缺乏。此外，几乎所有现有的数据集都有一些局限性，包括场景类和图像数量规模小，缺乏图像变化和多样性，以及精度饱和。这些限制严重限制了新方法的发展，尤其是基于深度学习的方法。本文首先提供了一个全面的审查最近的进展。然后，我们提出了一个大规模的数据集，称为“NWPU-RESISC 45”，这是一个公开的基准遥感图像场景分类（RESISC），由西北工业大学（NWPU）创建。该数据集包含31500幅图像，覆盖45个场景类，每个类700幅图像。所提出的NWPU-RESISC 45 1）在场景类别和总图像数量上是大规模的; 2）在平移、空间分辨率、视点、对象姿态、光照、背景和遮挡方面具有大的变化; 3）具有高的类内多样性和类间相似性。该数据集的创建将使社区能够开发和评估各种数据驱动的算法。最后，几个代表性的方法进行评估，使用建议的数据集，并报告的结果作为一个有用的基线，为今后的研究。
Remote sensing image scene classification plays an important role in a wide range of applications and hence has been receiving remarkable attention. During the past years, significant efforts have been made to develop various data sets or present a variety of approaches for scene classification from remote sensing images. However, a systematic review of the literature concerning data sets and methods for scene classification is still lacking. In addition, almost all existing data sets have a number of limitations, including the small scale of scene classes and the image numbers, the lack of image variations and diversity, and the saturation of accuracy. These limitations severely limit the development of new approaches especially deep learning-based methods. This paper first provides a comprehensive review of the recent progress. Then, we propose a large-scale data set, termed “NWPU-RESISC45,” which is a publicly available benchmark for REmote Sensing Image Scene Classification (RESISC), created by Northwestern Polytechnical University (NWPU). This data set contains 31 500 images, covering 45 scene classes with 700 images in each class. The proposed NWPU-RESISC45 1) is large-scale on the scene classes and the total image number; 2) holds big variations in translation, spatial resolution, viewpoint, object pose, illumination, background, and occlusion; and 3) has high within-class diversity and between-class similarity. The creation of this data set will enable the community to develop and evaluate various data-driven algorithms. Finally, several representative methods are evaluated using the proposed data set, and the results are reported as a useful baseline for future research.