On the use of the stochastic matched filter for ship wake detection in SAR images
- 1 September 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 01977385,p. 1-6
Abstract
Detecting straight patterns like ship wakes on a SAR image is not easy because there is no a priori information on orientation and position, moreover, SAR images are speckle noised. This article describes a ship wake detection technique based on the discrete Radon transform and stochastic matched filtering (SMF) used in detection. The association of these two processing methods leads to a detection algorithm that only requires the knowledge of the second order statistics of the signal and the noise. Experimentation on real SAR images shows the efficiency of the techniqueKeywords
This publication has 4 references indexed in Scilit:
- Detection of linear features in synthetic-aperture radar images by use of the localized Radon transform and prior informationApplied Optics, 2004
- Pattern recognition by means of the Radon transform and the continuous wavelet transformSignal Processing, 1999
- Localized Radon transform-based detection of ship wakes in SAR imagesIEEE Transactions on Geoscience and Remote Sensing, 1995
- Application Of Radon Transform Techniques To Wake Detection In Seasat-A SAR ImagesIEEE Transactions on Geoscience and Remote Sensing, 1990