Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval
Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval
复制标题
DOI：
10.3390/rs9050489
复制
发表时间：
2017-05-01
期刊：
影响因子：
5
通讯作者：
Shao, Zhenfeng
中科院分区：
文献类型：
--
作者：
Zhou, Weixun;Newsam, Shawn;Shao, Zhenfeng
学习强大的特征表示用于图像检索一直是遥感领域的一个具有挑战性的任务。传统的遥感图像特征提取方法主要集中在低层手工特征的提取上，由于遥感图像的复杂性，这些方法不仅耗时，而且往往不能取得令人满意的效果。在本文中，我们研究了如何基于卷积神经网络（CNN）提取深度特征表示用于高分辨率遥感图像检索（HRRSIR）。为此，提出了几个有效的计划，以产生强大的功能表示HRRSIR。在第一种方案中，在不同问题上预训练的CNN被视为特征提取器，因为没有大小合适的遥感数据集从头开始训练CNN。在第二种方案中，我们首先对遥感数据集上的预训练CNN进行微调，然后提出一种基于卷积层和三层感知器的新型CNN架构，从而研究特定于我们问题的学习特征。新的CNN比预训练和微调的CNN具有更少的参数，并且可以从有限的标记图像中学习低维特征。该计划进行了评估几个具有挑战性的，公开的数据集。结果表明，所提出的方案，特别是新颖的CNN，达到了最先进的性能。
Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but also tend to achieve unsatisfactory performance due to the complexity of remote sensing images. In this paper, we investigate how to extract deep feature representations based on convolutional neural networks (CNNs) for high-resolution remote sensing image retrieval (HRRSIR). To this end, several effective schemes are proposed to generate powerful feature representations for HRRSIR. In the first scheme, a CNN pre-trained on a different problem is treated as a feature extractor since there are no sufficiently-sized remote sensing datasets to train a CNN from scratch. In the second scheme, we investigate learning features that are specific to our problem by first fine-tuning the pre-trained CNN on a remote sensing dataset and then proposing a novel CNN architecture based on convolutional layers and a three-layer perceptron. The novel CNN has fewer parameters than the pre-trained and fine-tuned CNNs and can learn low dimensional features from limited labelled images. The schemes are evaluated on several challenging, publicly available datasets. The results indicate that the proposed schemes, particularly the novel CNN, achieve state-of-the-art performance.