Application of Model-Based Change Detection to Airborne VNIR/SWIR Hyperspectral Imagery

Meola, Joseph; Eismann, Michael T.; Moses, Randolph L.; Ash, Joshua N.

doi:10.1109/tgrs.2012.2186305

Cited by 26 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since hyperspectral images are characterized in hundreds of continuous observation bands, throughout the electromagnetic spectrum with high spectral resolution, such data have attracted considerable attention in the remote sensing community [1]. On the other hand, the analysis of hyperspectral images is of high importance in many practical applications, such as urban development [2]- [5], monitoring of land changes [6]- [9], and resource management [10], [11]. To benefit from these types of data, supervised hyperspectral image classification is among the most active research areas in hyperspectral analysis.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Spectral–Spatial Feature Learning via Deep Residual Conv–Deconv Network for Hyperspectral Image Classification

Mou

Ghamisi

Zhu

2018

IEEE Trans. Geosci. Remote Sensing

259

105

View full text Add to dashboard Cite

Supervised approaches classify input data using a set of representative samples for each class, known as training samples. The collection of such samples is expensive and time demanding. Hence, unsupervised feature learning, which has a quick access to arbitrary amounts of unlabeled data, is conceptually of high interest. In this paper, we propose a novel network architecture, fully Conv-Deconv network, for unsupervised spectral-spatial feature learning of hyperspectral images, which is able to be trained in an end-to-end manner. Specifically, our network is based on the so-called encoderdecoder paradigm, i.e., the input 3-D hyperspectral patch is first transformed into a typically lower dimensional space via a convolutional subnetwork (encoder), and then expanded to reproduce the initial data by a deconvolutional subnetwork (decoder). However, during the experiment, we found that such a network is not easy to be optimized. To address this problem, we refine the proposed network architecture by incorporating: 1) residual learning and 2) a new unpooling operation that can use memorized max-pooling indexes. Moreover, to understand the "black box," we make an in-depth study of the learned feature maps in the experimental analysis. A very interesting discovery is that some specific "neurons" in the first residual block of the proposed network own good description power for semantic visual patterns in the object level, which provide an opportunity to achieve "free" object detection. This paper, for the first time in the remote sensing community, proposes an end-to-end fully Conv-Deconv network for unsupervised spectral-spatial feature learning. Moreover, this paper also introduces an in-depth investigation of learned features. Experimental results on two widely used hyperspectral data, Indian Pines and Pavia University, demonstrate competitive performance obtained by the proposed methodology compared with other studied approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised Spectral–Spatial Feature Learning via Deep Residual Conv–Deconv Network for Hyperspectral Image Classification

Mou

Ghamisi

Zhu

2018

IEEE Trans. Geosci. Remote Sensing

259

105

View full text Add to dashboard Cite

show abstract

“…For learned features and transformations, various features or transformed feature spaces are learned to highlight the change information to detect a changed region more easily than when using the original spectral information of multi-temporal images, such as in Principal Component Analysis (PCA) [14], Multivariate Alteration Detection (MAD) [15], subspace learning [16,17], sparse learning [18] and slow features [19]. (4) Other advanced methods: Change detection can be formulated as a statistical hypothesis test using physical models [20]. The metric learning method [21] is also an effective method of detecting changes using well-learned distances.…”

Section: Introductionmentioning

confidence: 99%

Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection

2016

View full text Add to dashboard Cite

When exploited in remote sensing analysis, a reliable change rule with transfer ability can detect changes accurately and be applied widely. However, in practice, the complexity of land cover changes makes it difficult to use only one change rule or change feature learned from a given multi-temporal dataset to detect any other new target images without applying other learning processes. In this study, we consider the design of an efficient change rule having transferability to detect both binary and multi-class changes. The proposed method relies on an improved Long Short-Term Memory (LSTM) model to acquire and record the change information of long-term sequence remote sensing data. In particular, a core memory cell is utilized to learn the change rule from the information concerning binary changes or multi-class changes. Three gates are utilized to control the input, output and update of the LSTM model for optimization. In addition, the learned rule can be applied to detect changes and transfer the change rule from one learned image to another new target multi-temporal image. In this study, binary experiments, transfer experiments and multi-class change experiments are exploited to demonstrate the superiority of our method. Three contributions of this work can be summarized as follows: (1) the proposed method can learn an effective change rule to provide reliable change information for multi-temporal images; (2) the learned change rule has good transferability for detecting changes in new target images without any extra learning process, and the new target images should have a multi-spectral distribution similar to that of the training images; and (3) to the authors' best knowledge, this is the first time that deep learning in recurrent neural networks is exploited for change detection. In addition, under the framework of the proposed method, changes can be detected under both binary detection and multi-class change detection.

show abstract

“…With this rich spectral information, different land cover categories can potentially be precisely differentiated. To benefit from this type of data, supervised hyperspectral image classification plays a significant role and has been investigated in many applications, including urban development [2]- [5], the monitoring of land changes [6]- [9], scene interpretation [10]- [13], and resource management [14], [15].…”

mentioning

confidence: 99%

Deep Recurrent Neural Networks for Hyperspectral Image Classification

Mou

Ghamisi

Zhu

2017

IEEE Trans. Geosci. Remote Sensing

1,135

485

View full text Add to dashboard Cite

In recent years, vector-based machine learning algorithms, such as random forests, support vector machines, and 1-D convolutional neural networks, have shown promising results in hyperspectral image classification. Such methodologies, nevertheless, can lead to information loss in representing hyperspectral pixels, which intrinsically have a sequence-based data structure. A recurrent neural network (RNN), an important branch of the deep learning family, is mainly designed to handle sequential data. Can sequence-based RNN be an effective method of hyperspectral image classification? In this paper, we propose a novel RNN model that can effectively analyze hyperspectral pixels as sequential data and then determine information categories via network reasoning. As far as we know, this is the first time that an RNN framework has been proposed for hyperspectral image classification. Specifically, our RNN makes use of a newly proposed activation function, parametric rectified tanh (PRetanh), for hyperspectral sequential data analysis instead of the popular tanh or rectified linear unit. The proposed activation function makes it possible to use fairly high learning rates without the risk of divergence during the training procedure. Moreover, a modified gated recurrent unit, which uses PRetanh for hidden representation, is adopted to construct the recurrent layer in our network to efficiently process hyperspectral data and reduce the total number of parameters. Experimental results on three airborne hyperspectral images suggest competitive performance in the proposed mode. In addition, the proposed network architecture opens a new window for future research, showcasing the huge potential of deep recurrent networks for hyperspectral data analysis. Index Terms-Convolutional neural network (CNN), deep learning, gated recurrent unit (GRU), hyperspectral image classification, long short-term memory (LSTM), recurrent neural network (RNN). I. INTRODUCTION I N THE past few decades, the analysis of hyperspectral imagery acquired by remote sensors has attracted considerable attention in the remote sensing community, as such data are characterized in hundreds of continuous observation bands throughout the electromagnetic spectrum with high spectral

show abstract

Application of Model-Based Change Detection to Airborne VNIR/SWIR Hyperspectral Imagery

Cited by 26 publications

References 34 publications

Unsupervised Spectral–Spatial Feature Learning via Deep Residual Conv–Deconv Network for Hyperspectral Image Classification

Unsupervised Spectral–Spatial Feature Learning via Deep Residual Conv–Deconv Network for Hyperspectral Image Classification

Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection

Deep Recurrent Neural Networks for Hyperspectral Image Classification

Contact Info

Product

Resources

About