A new change-detection method in high-resolution remote sensing images based on a conditional random field model

ABSTRACT A new change-detection method for remote sensing images based on a conditional random field (CRF) model is proposed in this paper. The method artfully uses memberships of Fuzzy C-means as unary potentials in the fully connected CRF (FCCRF) model without training parameters, and pairwise potentials of the CRF model are defined by a linear combination of Gaussian kernels, with which a highly efficient approximate inference algorithm can be used. The proposed FCCRF model is expressed on the complete set of pixels in both the observed multitemporal images, which can incorporate long range contextual information of remote-sensing images and enable greatly refined change-detection results. Experimental results demonstrate that the proposed approach leads to more accurate pixel-level change-detection performance and is more robust against noise than traditional algorithms.

[1]  Lorenzo Bruzzone,et al.  Automatic analysis of the difference image for unsupervised change detection , 2000, IEEE Trans. Geosci. Remote. Sens..

[2]  Kai-Kuang Ma,et al.  Multitemporal Image Change Detection Using Undecimated Discrete Wavelet Transform and Active Contours , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Yupeng Li,et al.  Automatic change detection in high-resolution remote-sensing images by means of level set evolution and support vector machine classification , 2014 .

[4]  Chengquan Huang,et al.  Use of a dark object concept and support vector machines to automate forest cover change analysis , 2008 .

[5]  Shuang Wang,et al.  Unsupervised Change Detection in SAR Image Based on Gauss-Log Ratio Image Fusion and Compressed Projection , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[6]  Jon Atli Benediktsson,et al.  An Unsupervised Technique Based on Morphological Filters for Change Detection in Very High Resolution Images , 2008, IEEE Geoscience and Remote Sensing Letters.

[7]  Qiang Chen,et al.  A highly repeatable feature detector: improved Harris–Laplace , 2010, Multimedia Tools and Applications.

[8]  Vladlen Koltun,et al.  Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials , 2011, NIPS.

[9]  Francesca Bovolo,et al.  Analysis and Adaptive Estimation of the Registration Noise Distribution in Multitemporal VHR Images , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Farid Melgani,et al.  Unsupervised Change Detection in Multispectral Remotely Sensed Imagery With Level Set Methods , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[11]  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.

[12]  Dongmei Chen,et al.  Change detection from remotely sensed images: From pixel-based to object-based approaches , 2013 .

[13]  Martial Hebert,et al.  Discriminative random fields: a discriminative framework for contextual interaction in classification , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[14]  Nicholas J. Tate,et al.  A critical synthesis of remotely sensed optical image change detection techniques , 2015 .

[15]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[16]  Shohreh Kasaei,et al.  Change detection in remote sensing images using modified polynomial regression and spatial multivariate alteration detection , 2009 .

[17]  Gabriele Moser,et al.  Unsupervised change-detection methods for remote-sensing images , 2002 .

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

[19]  Ashish Ghosh,et al.  A Neural Approach Under Active Learning Mode for Change Detection in Remotely Sensed Images , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[20]  Bryan C. Pijanowski,et al.  Calibrating a neural network‐based urban change model for two metropolitan areas of the Upper Midwest of the United States , 2005, Int. J. Geogr. Inf. Sci..

[21]  Thuy Le Toan,et al.  Temporal Coherence of Tropical Forests at P-Band: Dry and Rainy Seasons , 2015, IEEE Geoscience and Remote Sensing Letters.

[22]  Ashish Ghosh,et al.  Fuzzy clustering algorithms for unsupervised change detection in remote sensing images , 2011, Inf. Sci..

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

[24]  John R. Jensen,et al.  Object‐based change detection using correlation image analysis and image segmentation , 2008 .

[25]  Chunhong Pan,et al.  Sparse Hierarchical Clustering for VHR Image Change Detection , 2015, IEEE Geoscience and Remote Sensing Letters.

[26]  Ni-Bin Chang,et al.  Change detection of land use and land cover in an urban region with SPOT-5 images and partial Lanczos extreme learning machine , 2010 .

[27]  G. Foody.  Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy , 2004 .

[28]  Geoffrey J. Hay,et al.  Object-based change detection , 2012 .

[29]  Daniel T. Lindsey,et al.  10.35 μm: an atmospheric window on the GOES-R Advanced Baseline Imager with less moisture attenuation , 2012 .

[30]  Alex M. Lechner,et al.  Comparison of relative radiometric normalization methods using pseudo-invariant features for change detection studies in rural and urban landscapes , 2012 .

[31]  Wenzhong Shi,et al.  Unsupervised Change Detection With Expectation-Maximization-Based Level Set , 2014, IEEE Geoscience and Remote Sensing Letters.