Change detection in very high-resolution images based on ensemble CNNs

ABSTRACT This paper presents a novel change detection method for very-high-resolution images based on deep learning. In the method, an ensemble CNN change detection framework is proposed. Different from other deep learning change detection methods, samples of changed and unchanged regions of two very-high-resolution images acquired at different times are fed into two CNN. The discriminative deep metric learning based on dissimilarity degree is used to adjust discriminative distance metric of two CNN output layers quantitatively, under which the distance of unchanged samples becomes smaller and that of changed samples becomes higher, respectively. During its training procedure, cost module function based on dissimilarity degree of samples is used to train the ensemble CNN and high-level and abstract features of changed and unchanged pair of samples are driven to learn by the proposed framework. After training, the discriminative distance of unchanged samples becomes smaller and that of changed samples becomes larger. The proposed method justifies the changed and unchanged area of original images and change detection results can be obtained. Experiments on real datasets and theoretical analysis validate the effectiveness and superiority of the proposed method.

[1]  Yang Liu,et al.  Study on Multi-Scale Window Determination for GLCM Texture Description in High-Resolution Remote Sensing Image Geo-Analysis Supported by GIS and Domain Knowledge , 2018, ISPRS Int. J. Geo Inf..

[2]  Maoguo Gong,et al.  Deep learning and mapping based ternary change detection for information unbalanced images , 2017, Pattern Recognit..

[3]  Paul L. Rosin,et al.  Evaluation of global image thresholding for change detection , 2003, Pattern Recognit. Lett..

[4]  G. H. Rosenfield,et al.  A coefficient of agreement as a measure of thematic classification accuracy. , 1986 .

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

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

[7]  Maoguo Gong,et al.  Difference representation learning using stacked restricted Boltzmann machines for change detection in SAR images , 2014, Soft Computing.

[8]  Djemel Ziou,et al.  Image Quality Metrics: PSNR vs. SSIM , 2010, 2010 20th International Conference on Pattern Recognition.

[9]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[10]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[11]  Lorenzo Bruzzone,et al.  An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR images , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Qing Wang,et al.  Change detection based on Faster R-CNN for high-resolution remote sensing images , 2018, Remote Sensing Letters.

[13]  John R. Jensen,et al.  A change detection model based on neighborhood correlation image analysis and decision tree classification , 2005 .

[14]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[15]  Bo Du,et al.  Saliency-Guided Unsupervised Feature Learning for Scene Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Yuyu Zhou,et al.  Remote sensing of land-cover change and landscape context of the National Parks: A case study of the Northeast Temperate Network , 2009 .

[17]  Frédéric Jurie,et al.  PCCA: A new approach for distance learning from sparse pairwise constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[19]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[20]  Timothy A. Warner,et al.  Kernel-Based Texture in Remote Sensing Image Classification , 2011 .

[21]  Gunter Menz,et al.  Robust Change Vector Analysis (RCVA) for multi-sensor very high resolution optical satellite data , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[22]  Mohammed Bennamoun,et al.  Forest Change Detection in Incomplete Satellite Images With Deep Neural Networks , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Maoguo Gong,et al.  Feature learning and change feature classification based on deep learning for ternary change detection in SAR images , 2017 .

[24]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[25]  D. King,et al.  Comparison of pixel- and object-based classification in land cover change mapping , 2011 .

[26]  P. Defourny,et al.  Monitoring forest changes in Borneo on a yearly basis by an object-based change detection algorithm using SPOT-VEGETATION time series , 2012 .

[27]  P. Fisher.  The pixel: A snare and a delusion , 1997 .

[28]  Maoguo Gong,et al.  Change Detection in Synthetic Aperture Radar Images Based on Deep Neural Networks , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Bo Du,et al.  Dimensionality Reduction and Classification of Hyperspectral Images Using Ensemble Discriminative Local Metric Learning , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Xiao Xiang Zhu,et al.  Long-Term Annual Mapping of Four Cities on Different Continents by Applying a Deep Information Learning Method to Landsat Data , 2018, Remote. Sens..

[31]  Tee-Ann Teo,et al.  Lidar-based change detection and change-type determination in urban areas , 2013 .

[32]  Natalia Sofina,et al.  Building Change Detection Using High Resolution Remotely Sensed Data and GIS , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[33]  Jocelyn Chanussot,et al.  Support Vector Reduction in SVM Algorithm for Abrupt Change Detection in Remote Sensing , 2009, IEEE Geoscience and Remote Sensing Letters.

[34]  Yuan Tian,et al.  Local Patch Discriminative Metric Learning for Hyperspectral Image Feature Extraction , 2014, IEEE Geoscience and Remote Sensing Letters.

[35]  Dong-Chen He,et al.  Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge , 2010 .

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

[37]  Jin Chen,et al.  Mapping impervious surface expansion using medium-resolution satellite image time series: a case study in the Yangtze River Delta, China , 2012 .