25 June 2014 Method for inshore ship detection based on feature recognition and adaptive background window
Author Affiliations +
J. of Applied Remote Sensing, 8(1), 083608 (2014). doi:10.1117/1.JRS.8.083608
Inshore ship detection in synthetic aperture radar (SAR) images is a challenging task. We present an inshore ship detection method based on the characteristics of inshore ships. We first use the Markov random field (MRF) method to segment water and land, and then extract the feature points of inshore ships using polygonal approximation. Following this, we propose new rules for inshore ship extraction and use these rules to separate inshore ships from the land in binary images. Finally, we utilize the adaptive background window (ABW) to complete the clutter statistic and successfully detect inshore ships using a constant false alarm rate (CFAR) detector with ABW and G0 distribution. Experimental results using SAR images show that our method is more accurate than traditional CFAR detection based on K-distribution (K-CFAR), given the same CFAR, and that the quality of the image obtained through our method is higher than that of the traditional K-CFAR detection method by a factor of 0.165. Our method accurately locates and detects inshore ships in complicated environments and thus is more practical for inshore ship detection.
© 2014 Society of Photo-Optical Instrumentation Engineers (SPIE)
Hongyu Zhao, Quan Wang, Jingjian Huang, Weiwei Wu, Naichang Yuan, "Method for inshore ship detection based on feature recognition and adaptive background window," Journal of Applied Remote Sensing 8(1), 083608 (25 June 2014). https://doi.org/10.1117/1.JRS.8.083608

Back to Top