Practical Considerations in Unsupervised Change Detection Using SAR Images

Change detection has a wide range of applications in hurricane damage assessment, urban growth monitoring, etc. It is well-known that synthetic aperture radar (SAR) can penetrate clouds and can work well under all weather conditions. However, SAR images also contain a lot of speckle noise that seriously affects change detection performance. In this paper, we focus on change detection using SAR images. In particular, we propose a new change detection algorithm that is applicable to both optical and SAR images. The detection performance of the algorithm was compared with a number of existing algorithms in the literature. Preliminary results using actual SAR images are encouraging. Most importantly, it was observed that effective change detection using SAR images require good denoising and post-processing algorithms in order to achieve decent performance.

[1]  Chiman Kwan,et al.  New Results in Change Detection Using Optical and Multispectral Images , 2019, 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON).

[2]  Maoguo Gong,et al.  Coupled Dictionary Learning for Change Detection From Multisource Data , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Maoguo Gong,et al.  Log-Based Transformation Feature Learning for Change Detection in Heterogeneous Images , 2018, IEEE Geoscience and Remote Sensing Letters.

[4]  Max Mignotte,et al.  An Energy-Based Model Encoding Nonlocal Pairwise Pixel Interactions for Multisensor Change Detection , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Chiman Kwan,et al.  Change Detection Using Original and Fused Landsat and Worldview Images , 2019, 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON).

[6]  Chiman Kwan,et al.  Remote Sensing Performance Enhancement in Hyperspectral Images , 2018, Sensors.

[7]  Chiman Kwan,et al.  A Novel Cluster Kernel RX Algorithm for Anomaly and Change Detection Using Hyperspectral Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Jae S. Lim,et al.  Two-Dimensional Signal and Image Processing , 1989 .

[9]  James Theiler,et al.  Multi-sensor anomalous change detection at scale , 2019, Defense + Commercial Sensing.

[10]  Yuzhong Shen,et al.  Change detection using Landsat and Worldview images , 2019, Defense + Commercial Sensing.

[11]  Chiman Kwan,et al.  A New Approach to Change Detection Using Heterogeneous Images , 2019, 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON).

[12]  Alan P. Schaum,et al.  Hyperspectral change detection and supervised matched filtering based on covariance equalization , 2004, SPIE Defense + Commercial Sensing.

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

[14]  Pierrick Coupé,et al.  Nonlocal Means-Based Speckle Filtering for Ultrasound Images , 2009, IEEE Transactions on Image Processing.

[15]  Chiman Kwan,et al.  A new nonlinear change detection approach based on band ratioing , 2018, Defense + Security.

[16]  Yuzhong Shen,et al.  Combining Satellite Images with Feature Indices for Improved Change Detection , 2018, 2018 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON).

[17]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[18]  Gang Li,et al.  Change Detection in Heterogenous Remote Sensing Images via Homogeneous Pixel Transformation , 2018, IEEE Transactions on Image Processing.

[19]  Chiman Kwan,et al.  High performance change detection in hyperspectral images using multiple references , 2018, Defense + Security.

[20]  Francesca Bovolo,et al.  The Time Variable in Data Fusion: A Change Detection Perspective , 2015, IEEE Geoscience and Remote Sensing Magazine.

[21]  Qian Du,et al.  Multi-Modal Change Detection, Application to the Detection of Flooded Areas: Outcome of the 2009–2010 Data Fusion Contest , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.