Hyperspectral anomaly detection based on stacked denoising autoencoders

Abstract. Hyperspectral anomaly detection (AD) is an important technique of unsupervised target detection and has significance in real situations. Due to the high dimensionality of hyperspectral data, AD will be influenced by noise, nonlinear correlation of band, or other factors that lead to the decline of detection accuracy. To overcome this problem, a method of hyperspectral AD based on stacked denoising autoencoders (AE) (HADSDA) is proposed. Simultaneously, two different feature detection models, spectral feature (SF) and fused feature by clustering (FFC), are constructed to verify the effectiveness of the proposed algorithm. The SF detection model uses the SF of each pixel. The FFC detection model uses a similar set of pixels constructed by clustering and then fuses the set of pixels by the stacked denoising autoencoders algorithm (SDA). The SDA is an algorithm that can automatically learn nonlinear deep features of the image. Compared with other linear or nonlinear feature extraction methods, the detection result of the proposed algorithm is greatly improved. Experiment results show that the proposed algorithm is an excellent feature learning method and can achieve higher detection performance.

[1]  Chunhui Zhao,et al.  Sparsity divergence index based on locally linear embedding for hyperspectral anomaly detection , 2016 .

[2]  Qi Li,et al.  Hyperspectral Imagery Classification Using Sparse Representations of Convolutional Neural Network Features , 2016, Remote. Sens..

[3]  Carlo Gatta,et al.  Unsupervised Deep Feature Extraction for Remote Sensing Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Nicolas Courty,et al.  Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions , 2015, ArXiv.

[5]  Xing Chen,et al.  Stacked Denoise Autoencoder Based Feature Extraction and Classification for Hyperspectral Images , 2016, J. Sensors.

[6]  Quan-Sen Sun,et al.  Hyperspectral classification via learnt features , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[7]  Ye Zhang,et al.  A novel anomaly detection approach based on clustering and decision-level fusion , 2015, SPIE Optical Engineering + Applications.

[8]  M. Siegel,et al.  Hyperspectral classification via deep networks and superpixel segmentation , 2015 .

[9]  Zhou Guo,et al.  On combining multiscale deep learning features for the classification of hyperspectral remote sensing imagery , 2015 .

[10]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[11]  Shanjun Mao,et al.  Spectral–spatial classification of hyperspectral images using deep convolutional neural networks , 2015 .

[12]  Xing Zhao,et al.  Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[13]  Edisanter Lo.  Hyperspectral anomaly detection based on uniformly partitioned pixel , 2014, Pattern Analysis and Applications.

[14]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[15]  Bo Du,et al.  A Discriminative Metric Learning Based Anomaly Detection Method , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Bo Du,et al.  Target detection based on a dynamic subspace , 2014, Pattern Recognit..

[17]  Saeid Homayouni,et al.  An Approach for Subpixel Anomaly Detection in Hyperspectral Images , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[18]  Wang Bin.  Hyperspectral Image Feature Extraction via Kernel Minimum Noise Fraction Transform , 2013 .

[19]  Wang,et al.  Kernel ICA Feature Extraction for Anomaly Detection in Hyperspectral Imagery , 2012 .

[20]  Stefania Matteoli,et al.  Complexity-aware algorithm architecture for real-time enhancement of local anomalies in hyperspectral images , 2011, Journal of Real-Time Image Processing.

[21]  Bo Du,et al.  A structured sub-pixel target detection method base on manifold learning method , 2011, International Symposium on Multispectral Image Processing and Pattern Recognition.

[22]  Tara N. Sainath,et al.  Deep Belief Networks using discriminative features for phone recognition , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[23]  Chein-I Chang,et al.  Multiparameter Receiver Operating Characteristic Analysis for Signal Detection and Classification , 2010, IEEE Sensors Journal.

[24]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[25]  Heesung Kwon,et al.  Kernel Eigenspace Separation Transform for Subspace Anomaly Detection in Hyperspectral Imagery , 2007, IEEE Geoscience and Remote Sensing Letters.

[26]  Nasser M. Nasrabadi,et al.  A comparative study of linear and nonlinear anomaly detectors for hyperspectral imagery , 2007, SPIE Defense + Commercial Sensing.

[27]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[28]  Marco Diani,et al.  Reducing Computational Complexity in Hyperspectral Anomaly Detection: a Feature Level Fusion Approach , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[29]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[30]  Gu Yan.  ANOMALY DETECTION ALGORITHM OF HYPERSPECTRAL IMAGES BASED ON SPECTRAL ANALYSES , 2006 .

[31]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[32]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.