@article{fdi:010091284,
  title = {{S}hip detection with {SAR} {C}-band satellite images : a systematic review},
  author = {{A}lexandre, {C}yprien and {D}evillers, {R}odolphe and {M}ouillot, {D}. and {S}eguin, {R}. and {C}atry, {T}hibault},
  editor = {},
  language = {{ENG}},
  abstract = {{D}etecting and tracking ships remotely is now required in a wide range of contexts, from military security to illegal immigration control, as well as the management of fisheries and marine protected areas. {A}mong the available methods, radar remote sensing is increasingly used due to its advantages of being rarely affected by cloud cover and allowing image acquisition during both day and night. {T}he growing availability over the past decade of free synthetic aperture radar ({SAR}) data, such as {S}entinel-1 images, enabled the widespread use of {C}-band images for ship detection. {T}here is, however, a broad range of {SAR} data processing methods proposed in the literature, challenging the selection of the most appropriate one for a given application. {H}ere, we conducted a systematic review of the literature on ship detection methods using {C}-band {SAR} data from 2015 to 2022. {T}he review shows a partition between traditional and deep learning ({DL}) methods. {E}arlier methods were mainly based on constant false alarm rate or polarimetry, which require limited computing resources but critically depend on ships' physical environment. {T}hose approaches are gradually replaced by {DL}, due to the growth of computing capacities, the wide availability of {SAR} images, and the publication of {DL} training datasets. {H}owever, access to these computing capacities may not be easy for all users, which could become a major obstacle to their development. {W}hile both methods have the same objective, they differ both technically and in their approaches to the problem. {T}raditional methods mainly focus on ship size in spatial units (meters), whereas {DL} methods are mainly based on the number of ship pixels, regardless of image resolution. {T}hese latter methods can result in a lack of information on ship size and, therefore, a lack of knowledge that could be useful to specific applications, such as fisheries and protected area management.},
  keywords = {{M}arine vehicles ; {R}adar polarimetry ; {S}ynthetic aperture radar ; {C}-band ; {A}rtificial intelligence ; {S}earch engines ; {R}emote sensing ; {M}aritime domain ; awareness ; remote sensing ; small ship ; synthetic aperture radar ({SAR}) ; vessel detection},
  booktitle = {},
  journal = {{IEEE} {J}ournal of {S}elected {T}opics in {A}pplied {E}arth {O}bservations and {R}emote {S}ensing},
  volume = {17},
  numero = {},
  pages = {14353--14367},
  ISSN = {1939-1404},
  year = {2024},
  DOI = {10.1109/jstars.2024.3437187},
  URL = {https://www.documentation.ird.fr/hor/fdi:010091284},
}