Multi-feature extraction of ships from SAR images

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Pose and structural features are widely used in automatic target recognition (ATR) systems. A procedure is proposed to extract such features of ships from synthetic aperture radar (SAR) images. The ship closed-contour image is first produced using a standard algorithm. A new two-step process is then presented for exact azimuth angle estimation. Modified criteria of centerline and minimum enclosing rectangle (MER) extraction are developed, and applied to calculate the ship dimension. Experimental results for numerically simulated SAR images demonstrate the effectiveness of the proposed technique.

Original languageEnglish
Title of host publicationProceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013
Pages454-458
Number of pages5
DOIs
StatePublished - 2013
Event2013 6th International Congress on Image and Signal Processing, CISP 2013 - Hangzhou, China
Duration: 16 Dec 201318 Dec 2013

Publication series

NameProceedings of the 2013 6th International Congress on Image and Signal Processing, CISP 2013
Volume1

Conference

Conference2013 6th International Congress on Image and Signal Processing, CISP 2013
Country/TerritoryChina
CityHangzhou
Period16/12/1318/12/13

Keywords

  • Automatic ship recognition
  • Feature extraction
  • Hough transform
  • Synthetic aperture radar image

Fingerprint

Dive into the research topics of 'Multi-feature extraction of ships from SAR images'. Together they form a unique fingerprint.

Cite this