Ship Detection from SAR Imagery Using CUDA and Performance Analysis of the System

Chaitanya P. Chandgude, P. M. Chawan
Department of Computer Technology, VJTI, Mumbai, India
Int. Journal of Engineering Research and Applications, Vol. 4, Issue 7 (Version 3), July 2014, pp.223-228


   title={Ship Detection from SAR Imagery Using CUDA and Performance Analysis of the System},

   author={Chandgude, Chaitanya P. and Chawan, P. M.},



Download Download (PDF)   View View   Source Source   



Synthetic aperture radar (SAR) Ship Detection System SDS is an important application from the point of view of Maritime Security monitoring. It allows monitoring traffic, fisheries, naval warfare. Since full-resolution SAR images are heavily affected by the presence of speckle, ship detection algorithms generally employ speckle reduced SAR images at the expense of a degradation of the spatial resolution. The proposed Parzen-window-kernel-based algorithm and CFAR algorithm can be considered an alternative to manual inspection for large ocean areas. Promising results and high detection rates for the ships have been achieved. In Parzen-window-kernel-based algorithm for ship detection in synthetic aperture radar (SAR) images, first, the data-driving kernel functions of Parzen window are utilized to approximate the histogram of real SAR image, in order to complete the accurate modeling of SAR images. Then ship detection is implemented using a Constant False Alarm Rate (CFAR). After detecting threshold, the output is added to edge detection algorithm employed on SAR image. Clearer detection of ship candidates is obtained by applying Parzen-window-kernel-based algorithm by changing its window size. Experimental results show that SDS implemented using CUDA is faster than on CPU.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: