A Fast Ship Detection Algorithm based on Automatic Censoring for Multiple Target Situations in SAR Images

Farah, Faiçal; Laroussi, Toufik; Madjidi, Hicham

doi:10.1109/ispa54004.2022.9786336

Cited by 4 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, researchers proposed corresponding detection algorithms to realize the precise detection of ship targets. Farah et al [ 15 ] presented a fast CFAR detection algorithm using GΓD model in SAR images with multiple ship targets. Considering the influence of ship targets for statistical modeling in the crowded harbors and busy shipping lines, Ai et al [ 16 , 17 ] proposed the new two parameter CFAR detector in Log-normal clutter, and the method adopted the clutter truncation processing.…”

Section: Introductionmentioning

confidence: 99%

Adaptive CFAR Method for SAR Ship Detection Using Intensity and Texture Feature Fusion Attention Contrast Mechanism

Pan

Yang

et al. 2022

Sensors

View full text Add to dashboard Cite

Due to the complexity of sea surface environments, such as speckles and side lobes of ships, ship wake, etc., the detection of ship targets in synthetic aperture radar (SAR) images is still confronted with enormous challenges, especially for small ship targets. Aiming at the key problem of ship target detection in the complex environments, the article proposes a constant false alarm rate (CFAR) algorithm for SAR ship target detection based on the attention contrast mechanism of intensity and texture feature fusion. First of all, the local feature attention contrast enhancement is performed based on the intensity dissimilarity and the texture feature difference described by local binary pattern (LBP) between ship targets and sea clutter, so as to realize the target enhancement and background suppression. Furthermore, the adaptive CFAR ship target detection method based on generalized Gamma distribution (GΓD) which can fit the clutter well by the goodness-of-fit analyses is carried out. Finally, the public datasets HRSID and LS-SSDD-v1.0 are used to verify the effectiveness of the proposed detection method. A large number of experimental results show that the proposed method can suppress clutter background and speckle noise and improve the target-to-clutter rate (TCR) significantly, and has the relative high detection rate and low false alarm rate in the complex background and multi-target marine environments.

show abstract

Section: Introductionmentioning

confidence: 99%