A Novel Approach to Unsupervised Change Detection Based on Hybrid Spectral Difference

The most commonly used features in unsupervised change detection are spectral characteristics. Traditional methods describe the degree of the change between two pixels by quantifying the difference in spectral values or spectral shapes (spectral curve shapes). However, traditional methods based on variation in spectral shapes tend to miss the change between two pixels if their spectral curves are close to flat; and traditional methods based on variation in spectral values tend to miss the change between two pixels if their values are low (dark objects). To inhibit the weaknesses of traditional methods, a novel approach to unsupervised change detection based on hybrid spectral difference (HSD) is proposed which combines the difference between spectral values and spectral shapes. First, a new method referred to as change detection based on spectral shapes (CDSS) is proposed that fuses the difference images produced by the spectral correlation mapper (SCM) and spectral gradient difference (SGD) in order to describe the variation in spectral shapes. Second, a method called change detection based on spectral values (CDSV), computing the Euclidean distance between two spectral vectors, is used to obtain a difference image based on the variation in spectral values. Then, the credibility of CDSS and CDSV for every pixel is calculated to describe how appropriate these two methods are for detecting the change. Finally, the difference images produced by CDSS and CDSV are fused with the corresponding credibility to generate the hybrid spectral difference image. Two experiments were carried out on worldview-2/3 and Landsat-7 Enhanced Thematic Mapper Plus (ETM+) datasets, and both qualitative and quantitative results indicated that HSD had superior capabilities of change detection compared with standard change vector analysis (CVA), SCM, SGD and multivariate alteration detection (MAD). The accuracy of CDSS is higher than CDSV in case-1 but lower in case-2 and, compared to the higher one, the overall accuracy and the kappa coefficient of HSD improved by 3.45% and 6.92%, respectively, in the first experiment, and by 1.66% and 3.31%, respectively, in the second experiment. The omission rate dropped by approx. 4.4% in both tests.

[1]  Andreas Rabe,et al.  Optimisation of Savannah Land Cover Characterisation with Optical and SAR Data , 2018, Remote. Sens..

[2]  Giles M. Foody,et al.  The impact of imperfect ground reference data on the accuracy of land cover change estimation , 2009 .

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

[4]  Chao-Cheng Wu,et al.  Effects of atmospheric correction and pansharpening on LULC classification accuracy using WorldView-2 imagery , 2015 .

[5]  G. Foody.  Assessing the accuracy of land cover change with imperfect ground reference data , 2010 .

[6]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

[7]  Victor Haertel,et al.  Gradual land cover change detection based on multitemporal fraction images , 2012, Pattern Recognit..

[8]  Wenzhong Shi,et al.  Novel Approach to Unsupervised Change Detection Based on a Robust Semi-Supervised FCM Clustering Algorithm , 2016, Remote. Sens..

[9]  Alfred Stein,et al.  Use of the Bradley-Terry model to quantify association in remotely sensed images , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Xuehong Chen,et al.  A spectral gradient difference based approach for land cover change detection , 2013 .

[11]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[12]  Jian Yang,et al.  Ship Classification Based on MSHOG Feature and Task-Driven Dictionary Learning with Structured Incoherent Constraints in SAR Images , 2018, Remote. Sens..

[13]  Farid Melgani,et al.  Markovian Fusion Approach to Robust Unsupervised Change Detection in Remotely Sensed Imagery , 2006, IEEE Geoscience and Remote Sensing Letters.

[14]  Kazhong Deng,et al.  Strategies Combining Spectral Angle Mapper and Change Vector Analysis to Unsupervised Change Detection in Multispectral Images , 2016, IEEE Geoscience and Remote Sensing Letters.

[15]  Peng Gong,et al.  Change Detection Using Principal Component Analysis and Fuzzy Set Theory , 1993 .

[16]  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.

[17]  D. Lu,et al.  Change detection techniques , 2004 .

[18]  C. Woodcock,et al.  Classification and Change Detection Using Landsat TM Data: When and How to Correct Atmospheric Effects? , 2001 .

[19]  Bei Zhao,et al.  Aurora Image Classification Based on Multi-Feature Latent Dirichlet Allocation , 2018, Remote. Sens..

[20]  Junwei Han,et al.  A Survey on Object Detection in Optical Remote Sensing Images , 2016, ArXiv.

[21]  Priyakant Sinha,et al.  Independent two-step thresholding of binary images in inter-annual land cover change/no-change identification , 2013 .

[22]  R. D. Johnson,et al.  Change vector analysis: A technique for the multispectral monitoring of land cover and condition , 1998 .

[23]  M. Ridd,et al.  A Comparison of Four Algorithms for Change Detection in an Urban Environment , 1998 .

[24]  Alan R. Gillespie,et al.  A New Approach to Change Vector Analysis Using Distance and Similarity Measures , 2011, Remote. Sens..

[25]  D. Al-Khudhairy,et al.  Structural Damage Assessments from Ikonos Data Using Change Detection, Object-Oriented Segmentation, and Classification Techniques , 2005 .

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

[27]  Lorenzo Bruzzone,et al.  An adaptive semiparametric and context-based approach to unsupervised change detection in multitemporal remote-sensing images , 2002, IEEE Trans. Image Process..

[28]  Francesca Bovolo,et al.  A Context-Sensitive Clustering Technique Based on Graph-Cut Initialization and Expectation-Maximization Algorithm , 2008, IEEE Geoscience and Remote Sensing Letters.

[29]  J. Aryal,et al.  A robust multi-kernel change detection framework for detecting leaf beetle defoliation using Landsat 7 ETM+ data , 2016 .

[30]  Christopher Conrad,et al.  Impact of feature selection on the accuracy and spatial uncertainty of per-field crop classification using Support Vector Machines , 2013 .

[31]  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.

[32]  Bo Du,et al.  Automatic Radiometric Normalization for Multitemporal Remote Sensing Imagery With Iterative Slow Feature Analysis , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[33]  C. Woodcock,et al.  An assessment of several linear change detection techniques for mapping forest mortality using multitemporal landsat TM data , 1996 .

[34]  Pol Coppin,et al.  Review ArticleDigital change detection methods in ecosystem monitoring: a review , 2004 .

[35]  Thomas Blaschke,et al.  Object-Based Change Detection in Urban Areas: The Effects of Segmentation Strategy, Scale, and Feature Space on Unsupervised Methods , 2016, Remote. Sens..

[36]  Ashish Ghosh,et al.  Histogram thresholding for unsupervised change detection of remote sensing images , 2011 .

[37]  Lisheng Song,et al.  A new model for the automatic relative radiometric normalization of multiple images with pseudo-invariant features , 2016 .