SAR image segmentation with parallel region merging

In this paper, a parallel region merging strategy is proposed for partitioning Synthetic Aperture Radar (SAR) images into several disjoint regions, based on the region adjacency graph (RAG) of an initial partition and the nearest neighbor graph (NNG) produced from the RAG. Developed from the multi-direction ratio edge detector, a multi-scale-multi-direction (MSMD) one is used to extract edge strength map (ESM) of an initial SAR image, feeded into watershed transform to generate an initial partition result of the initial SAR image. Considering local image properties, which makes the generated NNG center around bi-node circles situated in interiors of homogeneous regions, many of which are independently located in different homogeneous regions, the predication of the parallelizability for bi-node circles is proposed to make the proposed parallel region merging strategy. The proposed parallel merging strategy simultaneously merges bi-node circles far away from boundaries of regions, characterized by the length of path from a node to the bi-node circle in the NNG. The performance of the proposed parallel merging strategy is analyzed theoretically and experimentally, and our experiments show that the proposed method outweighs other compared methods.

[1]  Fátima N. S. de Medeiros,et al.  SAR imagery segmentation by statistical region growing and hierarchical merging , 2010, Digit. Signal Process..

[2]  Xiao Pan,et al.  Superpixels of RGB-D Images for Indoor Scenes Based on Weighted Geodesic Driven Metric , 2017, IEEE Transactions on Visualization and Computer Graphics.

[3]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[4]  David Eppstein,et al.  On Nearest-Neighbor Graphs , 1992, ICALP.

[5]  Frank Nielsen,et al.  Statistical region merging , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Peng Zhang,et al.  Adaptive Hybrid Conditional Random Field Model for SAR Image Segmentation , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Silvana G. Dellepiane.  An Automatic Data-Driven Method for SAR Image Segmentation in Sea Surface Analysis , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Silvana G. Dellepiane,et al.  Synthetic aperture radar image segmentation by a detail preserving Markov random field approach , 1997, IEEE Trans. Geosci. Remote. Sens..

[9]  Huangang Wang,et al.  Parameter Selection of Gaussian Kernel for One-Class SVM , 2015, IEEE Transactions on Cybernetics.

[10]  Emre Akyilmaz.  Multilogit Prior-Based Gamma Mixture Model for Segmentation of SAR Images , 2019, IEEE Geoscience and Remote Sensing Letters.

[11]  Jorma Rissanen,et al.  Minimum Description Length Principle , 2010, Encyclopedia of Machine Learning.

[12]  Hong Qiao,et al.  A Variational Model for PolSAR Data Speckle Reduction Based on the Wishart Distribution , 2015, IEEE Transactions on Image Processing.

[13]  Fang Liu,et al.  SAR Image segmentation based on convolutional-wavelet neural network and markov random field , 2017, Pattern Recognit..

[14]  Xiaoxiao Li,et al.  Deep Learning Markov Random Field for Semantic Segmentation , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Nikos Komodakis,et al.  A Framework for Efficient Structured Max-Margin Learning of High-Order MRF Models , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  J. Nobre,et al.  SAR Image Segmentation Based on Level Set Approach and {\cal G}_A^0 Model , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Jun Wang,et al.  A Joint Convolutional Neural Network for Simultaneous Despeckling and Classification of SAR Targets , 2020 .

[18]  Yan Chen,et al.  A Multi-Region Segmentation Method for SAR Images Based on the Multi-Texture Model With Level Sets , 2018, IEEE Transactions on Image Processing.

[19]  C. Oliver,et al.  Optimum edge detection in SAR , 1996 .

[20]  Penglang Shui,et al.  Region-Merging Method With Texture Pattern Attention for SAR Image Segmentation , 2021, IEEE Geoscience and Remote Sensing Letters.

[21]  Gabriela Palacio,et al.  Unsupervised Classification of SAR Images Using Markov Random Fields and ${\cal G}_{I}^{0}$ Model , 2011, IEEE Geoscience and Remote Sensing Letters.

[22]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Georgios Tziritas,et al.  Natural Image Segmentation Based on Tree Equipartition, Bayesian Flooding and Region Merging , 2011, IEEE Transactions on Image Processing.

[24]  W. Li,et al.  Watershed-based hierarchical SAR image segmentation , 1999 .

[25]  Nicu Sebe,et al.  Graph-without-cut: An Ideal Graph Learning for Image Segmentation , 2016, AAAI.

[26]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[27]  Penglang Shui,et al.  Fast SAR Image Segmentation via Merging Cost With Relative Common Boundary Length Penalty , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Shuang Wang,et al.  Context-Based Hierarchical Unequal Merging for SAR Image Segmentation , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Jianxin Chen,et al.  CNN-G: Convolutional Neural Network Combined With Graph for Image Segmentation With Theoretical Analysis , 2021, IEEE Transactions on Cognitive and Developmental Systems.

[31]  Heng Tao Shen,et al.  Coarse-to-fine Image Co-segmentation with Intra and Inter Rank Constraints , 2018, IJCAI.

[32]  Nicos Maglaveras,et al.  Watershed-based image segmentation with fast region merging , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[33]  Ferran Marqués,et al.  Region Merging Techniques Using Information Theory Statistical Measures , 2010, IEEE Transactions on Image Processing.

[34]  David Zhang,et al.  Automatic Image Segmentation by Dynamic Region Merging , 2010, IEEE Transactions on Image Processing.

[35]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[36]  Gang Liu,et al.  Meaningful Object Segmentation From SAR Images via a Multiscale Nonlocal Active Contour Model , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[37]  David A. Clausi,et al.  IRGS: Image Segmentation Using Edge Penalties and Region Growing , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Kun Li,et al.  Graph-Based Segmentation for RGB-D Data Using 3-D Geometry Enhanced Superpixels , 2015, IEEE Transactions on Cybernetics.

[39]  Rachid Deriche,et al.  Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation , 2002, International Journal of Computer Vision.

[40]  Rod Cook,et al.  MUM (Merge Using Moments) segmentation for SAR images , 1994, Remote Sensing.

[41]  Xiao Pan,et al.  Superpixels of RGB-D Images for Indoor Scenes Based on Weighted Geodesic Driven Metric , 2017, IEEE Trans. Vis. Comput. Graph..

[42]  Xuelong Li,et al.  Selective Level Set Segmentation Using Fuzzy Region Competition , 2016, IEEE Access.

[43]  Frédéric Galland,et al.  Minimum description length synthetic aperture radar image segmentation , 2003, IEEE Trans. Image Process..

[44]  A. Lopes,et al.  A statistical and geometrical edge detector for SAR images , 1988 .

[45]  Lei Shi,et al.  Polarimetric SAR Image Segmentation Using Statistical Region Merging , 2014, IEEE Geoscience and Remote Sensing Letters.

[46]  Philippe Marthon,et al.  An optimal multiedge detector for SAR image segmentation , 1998, IEEE Trans. Geosci. Remote. Sens..