Skip to Main content Skip to Navigation
Journal articles

Modélisation de texture basée sur les ondelettes pour la détection de parcelles viticoles à partir d'images Pleiades panchromatiques

Abstract : This study evaluates the potential of wavelet-based SIRV texture modeling for the detection of vineyards in very high resolution Pléiades data and compares the performances of these models with reference methods such as grey level co-occurrence matrices and a segmentation approach based on Gabor filter. The obtained results show that SIRV models enable to reach high detection rates while reducing the false alarm rate in comparison to the other approaches. These models also display a higher robustness to texture attenuation effects due to the low ratio between inter-row distance and spatial resolution observed in the studied wine-growing regions.
Document type :
Journal articles
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-01084325
Contributor : Lionel Bombrun Connect in order to contact the contributor
Submitted on : Wednesday, November 19, 2014 - 8:36:05 AM
Last modification on : Monday, November 26, 2018 - 1:30:05 PM
Long-term archiving on: : Friday, February 20, 2015 - 10:11:03 AM

File

Regniers14_RFPT.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01084325, version 1

Citation

Olivier Regniers, Lionel Bombrun, Christian Germain. Modélisation de texture basée sur les ondelettes pour la détection de parcelles viticoles à partir d'images Pleiades panchromatiques. Revue Française de Photogrammétrie et de Télédétection, Société Française de Photogrammétrie et de Télédétection, 2014, pp.117-122. ⟨hal-01084325⟩

Share

Metrics

Record views

321

Files downloads

521