Elongated strip oil spill segmentation based on a cooperative model

Di Mengmeng, Song Huajun, Ren Peng, Chunbo Luo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


This paper describes a novel framework to segment elongated strips of marine oil spill based on a cooperative model. We construct a higher-order energy function which characterizes data consistency and smoothness of varying orders in an integrated framework. We model the data consistency in terms of a finite Gamma mixture and then estimate its parameter values using an expectation maximization (EM) algorithm. In order to characterise the smoothness term we exploit a cooperative model which not only penalizes the length but also addresses the diversity of the object boundary. This advantage makes our framework more effective for segmenting elongated strip oil spill than traditional energy minimization methods such as graph cuts. Our framework is further evaluated using practical SAR images of oil spill recordings and its effectiveness is validated.
Original languageEnglish
Title of host publicationInternational Conference on Multisensor Fusion and Information Integration for Intelligent Systems (MFI), 2014
Number of pages5
ISBN (Print)978-1-4799-6731-5
Publication statusPublished - 2014


  • crude oil
  • expectation-maximisation algorithm
  • graph theory
  • image segmentation
  • radar imaging
  • synthetic aperture radar
  • EM algorithm
  • cooperative model
  • data consistency
  • elongated strip oil spill segmentation
  • energy function
  • energy minimization methods
  • expectation maximization algorithm
  • finite Gamma mixture
  • graph cuts
  • integrated framework
  • object boundary
  • oil spill recordings
  • practical SAR images
  • smoothness
  • Biological system modeling
  • Computational modeling
  • Mathematical model
  • Strips
  • Vegetation
  • Oil spill segmentation


Dive into the research topics of 'Elongated strip oil spill segmentation based on a cooperative model'. Together they form a unique fingerprint.

Cite this