Best-Performing Color Space for Land-Sea Segmentation

S. Toure (1) , O. Diop (1) , K. Kpalma (2) , A.S. Maiga (1)

1 UGB - Université Gaston Berger de Saint-Louis Sénégal
2 IETR - Institut d'Électronique et des Technologies du numéRique

Land-sea segmentation is one of the most challenging tasks in remote sensing. It is of great importance for many applications like coastline extraction and near shore ship detection. To facilitate future land-sea segmentation related research, we present, in this paper, an experimental study conducted on five color spaces (RGB, XYZ, La∗b∗, HSV and YCbCr) in order to show the best-performing color space for land-sea segmentation. The test is carried out on 50 images. The average segmentation results are given. The results show that the luminance-chrominance space (YCbCr, La∗b∗, HSV) are more appropriated than primary space (RGB, XYZ), in general. It is particularly noted that the perceptual color space HSV allows better results in land-sea segmentation application. © 2018 IEEE.

Mots clés: color space; feature extraction; FOOS; K-means; Land-sea segmentation

Domaines: Sciences de l'ingénieur [physics]

S. Toure, O. Diop, K. Kpalma, A.S. Maiga. Best-Performing Color Space for Land-Sea Segmentation. 41st International Conference on Telecommunications and Signal Processing, TSP 2018, Jul 2018, Athens, Greece. pp.8441437, ⟨10.1109/TSP.2018.8441437⟩. ⟨hal-01904640⟩