Urban Building Change Detection in SAR Images Using Combined Differential Image and Residual U-Net Network

With the rapid development of urbanization in China, monitoring urban changes is of great significance to city management, urban planning, and cadastral map updating. Spaceborne synthetic aperture radar (SAR) sensors can capture a large area of radar images quickly with fine spatiotemporal resolution and are not affected by weather conditions, making multi-temporal SAR images suitable for change detection. In this paper, a new urban building change detection method based on an improved difference image and residual U-Net network is proposed. In order to overcome the intensity compression problem of the traditional log-ratio method, the spatial distance and intensity similarity are combined to generate a weighting function to obtain a weighted difference image. By fusing the weighted difference image and the bitemporal original images, the three-channel color difference image is generated for building change detection. Due to the complexity of urban environments and the small scale of building changes, the residual U-Net network is used instead of fixed statistical models and the construction and classifier of the network are modified to distinguish between different building changes. Three scenes of Sentinel-1 interferometric wide swath data are used to validate the proposed method. The experimental results and comparative analysis show that our proposed method is effective for urban building change detection and is superior to the original U-Net and SVM method.

[1]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[2]  R. Dekker.  Speckle filtering in satellite SAR change detection imagery , 1998 .

[3]  Fabrizio Argenti,et al.  Speckle removal from SAR images in the undecimated wavelet domain , 2002, IEEE Trans. Geosci. Remote. Sens..

[4]  Francesca Bovolo,et al.  A detail-preserving scale-driven approach to change detection in multitemporal SAR images , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[5]  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.

[6]  Jordi Inglada,et al.  A New Statistical Similarity Measure for Change Detection in Multitemporal SAR Images and Its Extension to Multiscale Change Analysis , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[7]  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.

[8]  Wenzhong Shi,et al.  Unsupervised change detection using fuzzy c-means and MRF from remotely sensed images , 2013 .

[9]  Hu Zhaoling.  An Unsupervised Change Detection Approach Based on KI Dual Thresholds under the Generalized Gauss Model Assumption in SAR Images , 2013 .

[10]  Maoguo Gong,et al.  Unsupervised change detection in SAR images based on locally fitting model and semi-EM algorithm , 2014 .

[11]  Maoguo Gong,et al.  Fuzzy Clustering With a Modified MRF Energy Function for Change Detection in Synthetic Aperture Radar Images , 2014, IEEE Transactions on Fuzzy Systems.

[12]  J. Yackel,et al.  The Jeffries–Matusita distance for the case of complex Wishart distribution as a separability criterion for fully polarimetric SAR data , 2014 .

[13]  Gang Chen,et al.  Improving Pixel-Based Change Detection Accuracy Using an Object-Based Approach in Multitemporal SAR Flood Images , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[15]  Allan Aasbjerg Nielsen,et al.  Change detection in bi-temporal data by canonical information analysis , 2015, 2015 8th International Workshop on the Analysis of Multitemporal Remote Sensing Images (Multi-Temp).

[16]  Vahid Akbari,et al.  Generalized minimum-error thresholding for unsupervised change detection from multilook polarimetric SAR data , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[17]  Mihai Datcu,et al.  A convolutional deep belief network for polarimetric SAR data feature extraction , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[18]  Jia Liu,et al.  Change detection based on deep feature representation and mapping transformation for multi-spatial-resolution remote sensing images , 2016 .

[19]  Dirk H. Hoekman,et al.  Wavelet Based Analysis of TanDEM-X and LiDAR DEMs across a Tropical Vegetation Heterogeneity Gradient Driven by Fire Disturbance in Indonesia , 2016, Remote. Sens..

[20]  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.

[21]  Y. Zhang,et al.  A SAR INTENSITY IMAGES CHANGE DETECTION METHOD BASED ON FUSION DIFFERENCE DETECTOR AND STATISTICAL PROPERTIES , 2017 .

[22]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Xu Zhen,et al.  A Novel Approach to Change Detection in SAR Images with CNN Classification , 2017 .

[24]  Hong Zhang,et al.  Integrating H-A-α with fully convolutional networks for fully PolSAR classification , 2017, 2017 International Workshop on Remote Sensing with Intelligent Processing (RSIP).

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

[26]  Hong Zhang,et al.  Sar image change detection method based on visual attention , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[27]  Junyu Dong,et al.  Change Detection in SAR Images Based on Deep Semi-NMF and SVD Networks , 2017, Remote. Sens..

[28]  Bo Zhang,et al.  Operational Built-Up Areas Extraction for Cities in China Using Sentinel-1 SAR Data , 2018, Remote. Sens..

[29]  Ralf Ludwig,et al.  An automatic change detection approach for rapid flood mapping in Sentinel-1 SAR data , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[30]  Yongil Kim,et al.  Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks , 2018, Remote. Sens..

[31]  Hongdong Fan,et al.  A Spatial-Temporal Adaptive Neighborhood-Based Ratio Approach for Change Detection in SAR Images , 2018, Remote. Sens..

[32]  Yang Yu,et al.  An improved neighborhood-based ratio approach for change detection in SAR images , 2018 .

[33]  Ying Liu,et al.  Unsupervised Segmentation Evaluation Using Area-Weighted Variance and Jeffries-Matusita Distance for Remote Sensing Images , 2018, Remote. Sens..

[34]  Yan Wang,et al.  A Hierarchical Fully Convolutional Network Integrated with Sparse and Low-Rank Subspace Representations for PolSAR Imagery Classification , 2018, Remote. Sens..

[35]  Dušan Gleich,et al.  Temporal Change Detection in SAR Images Using Log Cumulants and Stacked Autoencoder , 2018, IEEE Geoscience and Remote Sensing Letters.

[36]  Hong Zhang,et al.  SAR Image Change Detection Using Saliency Extraction and Shearlet Transform , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[37]  Carlos López-Martínez,et al.  Towards a 20 m Global Building Map from Sentinel-1 SAR Data , 2018, Remote. Sens..

[38]  Qingjie Liu,et al.  Road Extraction by Deep Residual U-Net , 2017, IEEE Geoscience and Remote Sensing Letters.

[39]  Jie Yang,et al.  An Unsupervised Change Detection Method Using Time-Series of PolSAR Images from Radarsat-2 and GaoFen-3 , 2018, Sensors.

[40]  Chao Wang,et al.  Multi-Temporal SAR Data Large-Scale Crop Mapping Based on U-Net Model , 2019, Remote. Sens..

[41]  Executive Summary.  World Urbanization Prospects: The 2018 Revision , 2019 .