arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1509.03602cs.CV
收藏

DeepSat -卫星图像学习框架

DeepSat - A Learning framework for Satellite Imagery

Louisiana State University(路易斯安那州立大学);Bay Area Environmental Research Institute(湾区环境研究所);NASA Ames Research Center(美国国家航空航天局艾姆斯研究中心);NASA Advanced Supercomputing Division(美国国家航空航天局高级计算部门)

Saikat Basu, Sangram Ganguly, Supratik Mukhopadhyay, Robert DiBiano, Manohar Karki, Ramakrishna Nemani

摘要:

卫星图像分类是遥感、计算机视觉和机器学习的交叉点上的一个具有挑战性的问题。由于卫星数据固有的高度可变性,大多数当前的对象分类方法不适合处理卫星数据集。卫星图像分析的进展也因缺乏具有多个类别标签的单一标签高分辨率数据集而受到抑制。本文的贡献是双重的-(1)首先,我们提出了两个新的卫星数据集,称为SAT-4和SAT-6,(2)然后,我们提出了一个分类框架,从输入图像中提取特征,将其归一化,并将归一化的特征向量馈送到深度信念网络进行分类。在SAT-4数据集上,我们最好的网络产生了97.95%的分类准确率,并优于三种最先进的对象识别算法,即深度置信网络,卷积神经网络和堆叠去噪自动编码器约11%。在SAT-6上,它的分类准确率为93.9%,比其他算法高出约15%。与随机森林分类器的比较研究显示了无监督学习方法相对于传统监督学习技术的优势。基于分布可分性准则和内禀相似性估计的统计分析证实了我们的方法在学习更好的卫星图像表示的有效性。

英文摘要:

Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification approaches are not suitable for handling satellite datasets. The progress of satellite image analytics has also been inhibited by the lack of a single labeled high-resolution dataset with multiple class labels. The contributions of this paper are twofold - (1) first, we present two new satellite datasets called SAT-4 and SAT-6, and (2) then, we propose a classification framework that extracts features from an input image, normalizes them and feeds the normalized feature vectors to a Deep Belief Network for classification. On the SAT-4 dataset, our best network produces a classification accuracy of 97.95% and outperforms three state-of-the-art object recognition algorithms, namely - Deep Belief Networks, Convolutional Neural Networks and Stacked Denoising Autoencoders by ~11%. On SAT-6, it produces a classification accuracy of 93.9% and outperforms the other algorithms by ~15%. Comparative studies with a Random Forest classifier show the advantage of an unsupervised learning approach over traditional supervised learning techniques. A statistical analysis based on Distribution Separability Criterion and Intrinsic Dimensionality Estimation substantiates the effectiveness of our approach in learning better representations for satellite imagery.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑