Wavelet based texture modeling for panchromatic very high resolution image classification : application to oyster racks detection

Olivier Regniers 1 Lionel Bombrun 1 Virginie Lafon 2 Aurélie Dehouck 2 Claire Tinel 3 Christian Germain 1
1 IMS - Laboratoire de l'intégration, du matériau au système
2 GEO Transfert
3 CNES - Centre National d'Études Spatiales [Toulouse]
Abstract : This study evaluates the potential of wavelet-based texture multivariate modeling for the detection of cultivated oyster fields and their differentiation from abandoned fields in Very High Resolution panchromatic PLEIADES data. The proposed models are tested in a supervised classification context using a training database composed of extracted image patches representative of the land covers of interest. The obtained classification results exhibit high detection rate for cultivated fields. Classification errors appear however in the detection of abandoned fields. These results demonstrate the interest of such model for the characterization of inter-tidal ecosystems and opens up perspectives for their use in the management of oyster farming activities.
Keywords : wavelet oyster culture Texture analysis classification very high resolution
Document type :
Conference papers
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download
https://hal.archives-ouvertes.fr/hal-01064413
Contributor : Lionel Bombrun <>
Submitted on : Tuesday, September 16, 2014 - 11:44:07 AM
Last modification on : Thursday, July 25, 2019 - 4:34:16 PM
Long-term archiving on : Wednesday, December 17, 2014 - 10:51:40 AM

File

Regniers14_IGARSS.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01064413, version 1

Collections

CNRS | IMS-BORDEAUX | IMS-BORDEAUX-FUSION

Citation

Olivier Regniers, Lionel Bombrun, Virginie Lafon, Aurélie Dehouck, Claire Tinel, et al.. Wavelet based texture modeling for panchromatic very high resolution image classification : application to oyster racks detection. IEEE International Geoscience and Remote Sensing conference, 2014, Québec, Canada. pp.5148-5151. ⟨hal-01064413⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

238

Files downloads

365

Contact

CCSD