Target recognition of floating raft aquaculture in SAR image based on statistical region merging

Yuanyuan Hu, Jianchao Fan, Jun Wang

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

12 Citations (Scopus)

Abstract

Floating raft aquaculture is a significant part of the mariculture, and its recognition is conducive to the dynamic monitoring of sea area. The satellite synthetic aperture radar (SAR) image can overcome the uncertainties of marine meteorological environment and reflect the location of floating raft aquaculture. However, oceanic SAR images are seriously contaminated by speckle noise, and effective features of SAR images are deficient, which make recognition difficult. Modified statistical region merging (SRM) algorithm is utilized to accomplish superpixels segmentation, which weakens the contamination of speckle noise. Non-subsampled contourlet transform is adopted to obtain contour feature to enrich the data information for subsequent processing. After that, using fuzzy compactness and separation can unsupervised recognize the target of floating raft aquaculture. In the experiment, the Radarsat-2 SAR data in the adjacent sea area of Changhai County in Liaoning Province is chosen to test the proposed method. The results demonstrate that the proposed method effectively improves the recognition accuracy, and obtains the area of floating raft aquaculture with smooth boundary and less isolated noise points.

Original languageEnglish
Title of host publication7th International Conference on Information Science and Technology, ICIST 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages429-432
Number of pages4
ISBN (Electronic)9781509054015
DOIs
Publication statusPublished - 11 May 2017
Externally publishedYes
Event7th International Conference on Information Science and Technology, ICIST 2017 - Da Nang, Viet Nam
Duration: 16 Apr 201719 Apr 2017

Publication series

Name7th International Conference on Information Science and Technology, ICIST 2017 - Proceedings

Conference

Conference7th International Conference on Information Science and Technology, ICIST 2017
Country/TerritoryViet Nam
CityDa Nang
Period16/04/1719/04/17

Keywords

  • floating raft aquaculture
  • statistical region merging
  • synthetic aperture radar
  • target recognition

Fingerprint

Dive into the research topics of 'Target recognition of floating raft aquaculture in SAR image based on statistical region merging'. Together they form a unique fingerprint.

Cite this