Ship Detection in SAR Images by Aggregating Densities of Fisher Vectors: Extension to a Global Perspective

Fisher vectors (FVs) can capture multiple order information from superpixels (SPs) in synthetic aperture radar (SAR) images. Existing FV-based ship detectors mainly exploit the local contrast of FVs (LCFVs) but do not consider their global density features. This may lead to degraded performance in terms of discrimination between ship targets and the complex sea clutter. In this article, two new global cues from FVs are designed based on the fact that target FVs exhibit much lower densities than those of clutter FVs and also have large distances to the latter. Our two new global cues can suppress the sea clutter and significantly enhance ship targets throughout the SAR image. We also design an improved local cue from FVs for ship detection, in which the intensity contrast of SPs is incorporated into the existing LCFV indicator to reduce false alarms. By fusing the above two new global cues (and an improved local cue from FVs), we propose a new method for ship detection in SAR images. Experimental results based on Gaofen-3 SAR images show that the newly proposed detector provides better detection performance than other state-of-the-art detectors, especially in the presence of strong and highly heterogeneous sea clutter.

[1]  Yi Su,et al.  Inshore Ship Detection via Saliency and Context Information in High-Resolution SAR Images , 2016, IEEE Geoscience and Remote Sensing Letters.

[2]  Charles Elkan,et al.  Expectation Maximization Algorithm , 2010, Encyclopedia of Machine Learning.

[3]  Hua Zhong,et al.  A Curvature-Based Saliency Method for Ship Detection in SAR Images , 2021, IEEE Geoscience and Remote Sensing Letters.

[4]  Cordelia Schmid,et al.  Segmentation Driven Object Detection with Fisher Vectors , 2013, 2013 IEEE International Conference on Computer Vision.

[5]  Lei Wang,et al.  Compositional Model Based Fisher Vector Coding for Image Classification , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Huanxin Zou,et al.  A Bilateral CFAR Algorithm for Ship Detection in SAR Images , 2015, IEEE Geoscience and Remote Sensing Letters.

[7]  Alin Achim,et al.  Superpixel-Level CFAR Detectors for Ship Detection in SAR Imagery , 2018, IEEE Geoscience and Remote Sensing Letters.

[8]  Tao Tang,et al.  Adaptive Superpixel Generation for SAR Images With Linear Feature Clustering and Edge Constraint , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Weidong Yu,et al.  A New CFAR Ship Detection Algorithm Based on 2-D Joint Log-Normal Distribution in SAR Images , 2010, IEEE Geoscience and Remote Sensing Letters.

[10]  Chengle Zhou,et al.  Hyperspectral Anomaly Detection Using Dual Window Density , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[11]  A. Duxbury,et al.  An Introduction to the World's Oceans , 1984 .

[12]  Yi Su,et al.  Adaptive Statistical Superpixel Merging With Edge Penalty for PolSAR Image Segmentation , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Tao Li,et al.  Target Detection by Exploiting Superpixel-Level Statistical Dissimilarity for SAR Imagery , 2018, IEEE Geoscience and Remote Sensing Letters.

[14]  Zhuo Pan,et al.  Superpixel-Based LCM Detector for Faint Ships Hidden in Strong Noise Background SAR Imagery , 2019, IEEE Geoscience and Remote Sensing Letters.

[15]  Yan Wang,et al.  A Modified CFAR Algorithm Based on Object Proposals for Ship Target Detection in SAR Images , 2016, IEEE Geoscience and Remote Sensing Letters.

[16]  Shi-Min Hu,et al.  Global contrast based salient region detection , 2011, CVPR 2011.

[17]  Ruigang Yang,et al.  Semi-Supervised Video Object Segmentation with Super-Trajectories , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Antonio Plaza,et al.  Ship Detection in SAR Images via Enhanced Nonnegative Sparse Locality-Representation of Fisher Vectors , 2021, IEEE Transactions on Geoscience and Remote Sensing.

[20]  G. Galdorisi,et al.  Bridging the Policy and Technology Gap : A Process to Instantiate Maritime Domain Awareness , 2005, Proceedings of OCEANS 2005 MTS/IEEE.

[21]  Jian Yang,et al.  Ship Detection in Polarimetric SAR Images via Variational Bayesian Inference , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[22]  A. Plaza,et al.  Adaptive Superpixel Segmentation with Fisher Vectors for Ship Detection in SAR Images , 2020, IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium.

[23]  Shuo Liu,et al.  Information Theory-Based Target Detection for High-Resolution SAR Image , 2016, IEEE Geoscience and Remote Sensing Letters.

[24]  Zhao Lin,et al.  Contextual Region-Based Convolutional Neural Network with Multilayer Fusion for SAR Ship Detection , 2017, Remote. Sens..

[25]  Jian-Xun Mi,et al.  Review Study of Interpretation Methods for Future Interpretable Machine Learning , 2020, IEEE Access.

[26]  Dongliang Peng,et al.  Superpixel-Level CFAR Detector Based on Truncated Gamma Distribution for SAR Images , 2021, IEEE Geoscience and Remote Sensing Letters.

[27]  Ming-Hsuan Yang,et al.  PiCANet: Pixel-Wise Contextual Attention Learning for Accurate Saliency Detection , 2018, IEEE Transactions on Image Processing.

[28]  Hongwei Liu,et al.  Superpixel-Based CFAR Target Detection for High-Resolution SAR Images , 2016, IEEE Geoscience and Remote Sensing Letters.

[29]  Yuan Yan Tang,et al.  A Local Contrast Method for Small Infrared Target Detection , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Yu-Jin Zhang,et al.  300-FPS Salient Object Detection via Minimum Directional Contrast , 2017, IEEE Transactions on Image Processing.

[31]  You He,et al.  Ship Detection in SAR Images via Local Contrast of Fisher Vectors , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .

[33]  Chengle Zhou,et al.  Hyperspectral Classification With Noisy Label Detection via Superpixel-to-Pixel Weighting Distance , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Haitao Lang,et al.  Ship Detection in High-Resolution SAR Images by Clustering Spatially Enhanced Pixel Descriptor , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[35]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[36]  Lanqing Huang,et al.  SAR Speckle Dependence on Ocean Surface Wind Field , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[37]  Katrine Bugge,et al.  Extreme disorder in an ultrahigh-affinity protein complex , 2018, Nature.

[38]  Kan Jin,et al.  Ship Detection With Superpixel-Level Fisher Vector in High-Resolution SAR Images , 2020, IEEE Geoscience and Remote Sensing Letters.

[39]  Jian Yang,et al.  Robust CFAR Detector Based on Truncated Statistics for Polarimetric Synthetic Aperture Radar , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[40]  Koray Kayabol,et al.  Mixture-Based Superpixel Segmentation and Classification of SAR Images , 2016, IEEE Geoscience and Remote Sensing Letters.

[41]  Colin P. Schwegmann,et al.  Manifold Adaptation for Constant False Alarm Rate Ship Detection in South African Oceans , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[42]  Marcos Portabella,et al.  A Novel Azimuth Cutoff Implementation to Retrieve Sea Surface Wind Speed From SAR Imagery , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[43]  Jianyu Yang,et al.  Ship Detection in Large-Scale SAR Images Via Spatial Shuffle-Group Enhance Attention , 2021, IEEE Trans. Geosci. Remote. Sens..

[44]  Wenhui,et al.  AIR-SARShip-1.0: High-resolution SAR Ship Detection Dataset , 2020 .

[45]  Antonio-Javier Gallego,et al.  Two-Stage Convolutional Neural Network for Ship and Spill Detection Using SLAR Images , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[46]  Thomas Mensink,et al.  Image Classification with the Fisher Vector: Theory and Practice , 2013, International Journal of Computer Vision.

[47]  Gang Li,et al.  SAR Image Despeckling Based on Combination of Fractional-Order Total Variation and Nonlocal Low Rank Regularization , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[48]  Chao Wang,et al.  A SAR Dataset of Ship Detection for Deep Learning under Complex Backgrounds , 2019, Remote. Sens..