Semi-supervised change detection method for multi-temporal hyperspectral images

Abstract Change detection is one of the most important open topics for multi-temporal remote sensing technology to observe the earth. Recently, many methods are proposed to detect the land-cover change information by multi-temporal hyperspectral images. However, many existing traditional change detection methods failed to utilize the spectral information effectively. Hence the models are not robust enough for more widely applications with “noise” bands. In this case, a semi-supervised distance metric learning method is proposed to detect the change areas by abundant spectral information of hyperspectral image under the “noisy” condition. This paper focuses on semi-supervised change detection method, and proposes a new distance metric learning framework for change detection in “noisy” condition with three mainly contributions: (1) Distance metric learning is demonstrated to be an effective method for revealing the change information by high spectral features. (2) An evolution regular framework is utilized to handle change detection under a “noisy” condition without removing any noise bands, which is impacted by atmosphere (or water) and always removed manually in other literatures. (3) A semi-supervised Laplacian Regularized Metric Learning method is exploited to tackle the ill-posed sample problem, and large unlabeled data is exploited in our method. The proposed method is performed on two multi-temporal hyperspectral datasets. Experimental results show that the proposed method outperforms the state-of-the-art change detection methods under both “ideal” and “noisy” conditions.

[1]  Ashish Ghosh,et al.  Semi-supervised change detection using modified self-organizing feature map neural network , 2014, Appl. Soft Comput..

[2]  M. Ashton,et al.  Hyperion, IKONOS, ALI, and ETM+ sensors in the study of African rainforests , 2004 .

[3]  Amir Globerson,et al.  Metric Learning by Collapsing Classes , 2005, NIPS.

[4]  Francesca Bovolo,et al.  A Framework for Automatic and Unsupervised Detection of Multiple Changes in Multitemporal Images , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[5]  K. Green,et al.  Using remote sensing to detect and monitor land-cover and land-use change , 1994 .

[6]  Turgay Çelik,et al.  Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and $k$-Means Clustering , 2009, IEEE Geoscience and Remote Sensing Letters.

[7]  Bo Du,et al.  A Subspace-Based Change Detection Method for Hyperspectral Images , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  Tomaso A. Poggio,et al.  Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[9]  Meng Wang,et al.  Multimodal Graph-Based Reranking for Web Image Search , 2012, IEEE Transactions on Image Processing.

[10]  Jun Yu,et al.  Complex Object Correspondence Construction in Two-Dimensional Animation , 2011, IEEE Transactions on Image Processing.

[11]  Knut Conradsen,et al.  Multivariate Alteration Detection (MAD) and MAF Postprocessing in Multispectral, Bitemporal Image Data: New Approaches to Change Detection Studies , 1998 .

[12]  T. Häme,et al.  An unsupervised change detection and recognition system for forestry , 1998 .

[13]  Francesca Bovolo,et al.  A Theoretical Framework for Unsupervised Change Detection Based on Change Vector Analysis in the Polar Domain , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[15]  Ashbindu Singh,et al.  Review Article Digital change detection techniques using remotely-sensed data , 1989 .

[16]  Paolo Gamba,et al.  Improving Change Detection Results of IR-MAD by Eliminating Strong Changes , 2011, IEEE Geoscience and Remote Sensing Letters.

[17]  Xiaoxiong Xiong,et al.  Assessment of Spectral Band Impact on Intercalibration Over Desert Sites Using Simulation Based on EO-1 Hyperion Data , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[18]  John Shepanski,et al.  Hyperion, a space-based imaging spectrometer , 2003, IEEE Trans. Geosci. Remote. Sens..

[19]  Liangpei Zhang,et al.  Fault-Tolerant Building Change Detection From Urban High-Resolution Remote Sensing Imagery , 2013, IEEE Geoscience and Remote Sensing Letters.

[20]  Susan L. Ustin,et al.  Early fire detection using non-linear multitemporal prediction of thermal imagery , 2007 .

[21]  Luo Si,et al.  Collaborative image retrieval via regularized metric learning , 2006, Multimedia Systems.

[22]  Allan Aasbjerg Nielsen,et al.  The Regularized Iteratively Reweighted MAD Method for Change Detection in Multi- and Hyperspectral Data , 2007, IEEE Transactions on Image Processing.

[23]  Gustavo Camps-Valls,et al.  Unsupervised Change Detection With Kernels , 2012, IEEE Geoscience and Remote Sensing Letters.

[24]  Thomas S. Huang,et al.  Partially Supervised Speaker Clustering , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Ashish Ghosh,et al.  A novel approach for change detection of remotely sensed images using semi-supervised multiple classifier system , 2014, Inf. Sci..

[26]  Johannes R. Sveinsson,et al.  Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles , 2008, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[27]  Francesca Bovolo,et al.  Detection of Land-Cover Transitions in Multitemporal Remote Sensing Images With Active-Learning-Based Compound Classification , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Gustavo Camps-Valls,et al.  Semi-Supervised Graph-Based Hyperspectral Image Classification , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Jinsong Deng,et al.  PCA‐based land‐use change detection and analysis using multitemporal and multisensor satellite data , 2008 .

[30]  Wei Liu,et al.  Learning Distance Metrics with Contextual Constraints for Image Retrieval , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[31]  Bo Du,et al.  Slow Feature Analysis for Change Detection in Multispectral Imagery , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Ya Shi,et al.  Smooth approximation method for non-smooth empirical risk minimization based distance metric learning , 2014, Neurocomputing.

[33]  Jean-Philippe Thiran,et al.  Semi-Supervised Novelty Detection Using SVM Entire Solution Path , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[34]  David W. Messinger,et al.  Iterative convex hull volume estimation in hyperspectral imagery for change detection , 2010, Defense + Commercial Sensing.

[35]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.

[36]  Volker Walter,et al.  Object-based classification of remote sensing data for change detection , 2004 .

[37]  Cordelia Schmid,et al.  Multimodal semi-supervised learning for image classification , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[38]  Wei Wang,et al.  Globality and locality incorporation in distance metric learning , 2014, Neurocomputing.

[39]  Wei Liu,et al.  Semi-supervised distance metric learning for collaborative image retrieval and clustering , 2010, ACM Trans. Multim. Comput. Commun. Appl..

[40]  Peng Gong,et al.  Using local transition probability models in Markov random fields for forest change detection , 2008 .

[41]  Francesca Bovolo,et al.  A Context-Sensitive Technique Robust to Registration Noise for Change Detection in VHR Multispectral Images , 2010, IEEE Transactions on Image Processing.

[42]  LiuWei,et al.  Semi-supervised distance metric learning for collaborative image retrieval and clustering , 2010 .

[43]  Russell C. Hardie,et al.  Hyperspectral Change Detection in the Presenceof Diurnal and Seasonal Variations , 2008, IEEE Transactions on Geoscience and Remote Sensing.