SAR Image Fast Online ATR Based on Visual Attention and Scale Analysis

Aiming at the online automatic target recognition for SAR images, a visual attention based scale analysis method is introduced for the feature extraction and the classifiers construction. By improving the features adaptability and robustness on speckle, a local multi-resolution analysis method is introduced for feature extraction of the SAR targets. Also a non-biased multi-scale LSSVC model is proposed to furthermore improve the classification performance. On this basis, a fast online learning algorithm based on Cholesky factorization is studied and applied to the SAR image recognition, which has smaller computation complexity than the common method with matrix inversion. Experiments testify that the presented method can give better classification precision and online performance.

[1]  Haipeng Wang,et al.  Target Classification Using the Deep Convolutional Networks for SAR Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Jianyu Yang,et al.  SAR Automatic Target Recognition Based on Multiview Deep Learning Framework , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Peter F. McGuire,et al.  Automatic Target Recognition in Synthetic Aperture Radar Imagery: A State-of-the-Art Review , 2016, IEEE Access.

[4]  Wang Hong.  On Multiple Kernel Learning Methods , 2010 .

[5]  David Morgan,et al.  Deep convolutional neural networks for ATR from SAR imagery , 2015, Defense + Security Symposium.

[6]  Li Yu,et al.  A multi-scale kernel learning method and its application in image classification , 2017, Neurocomputing.

[7]  Ethem Alpaydin,et al.  Multiple Kernel Learning Algorithms , 2011, J. Mach. Learn. Res..

[8]  Yan-Ning Cai,et al.  On Multiple Kernel Learning Methods: On Multiple Kernel Learning Methods , 2010 .

[9]  Guangyuan Fu,et al.  Visual-Cognition-Driven SAR Multiple Targets Robust Feature Extraction, Recognition and Tracking , 2016, ICCSIP.

[10]  Hongyuan Zha,et al.  MREKLM: A fast multiple empirical kernel learning machine , 2017, Pattern Recognit..

[11]  Fuchun Sun,et al.  Online chaotic time series prediction using unbiased composite kernel machine via Cholesky factorization , 2010, Soft Comput..

[12]  Yong Dou,et al.  Multiple kernel learning with hybrid kernel alignment maximization , 2017, Pattern Recognit..

[13]  Nian Zhang,et al.  Multi-kernel learning for multivariate performance measures optimization , 2017, Neural Computing and Applications.

[14]  Chen Qiang,et al.  Chaos modeling and real-time online prediction of permanent magnet synchronous motor based on multiple kernel least squares support vector machine , 2010 .

[15]  Saeid Homayouni,et al.  Similarity-Based Multiple Kernel Learning Algorithms for Classification of Remotely Sensed Images , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[16]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[17]  Rong Jin,et al.  Online Multiple Kernel Classification , 2013, Machine Learning.