Benchmarking of Remote Sensing Segmentation Methods

0445995 - ÚTIA 2016 RIV US eng J - Journal Article
Mikeš, Stanislav - Haindl, Michal - Scarpa, G. - Gaetano, R.
Benchmarking of Remote Sensing Segmentation Methods.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. Roč. 8, č. 5 (2015), s. 2240-2248. ISSN 1939-1404. E-ISSN 2151-1535
R&D Projects: GA ČR(CZ) GA14-10911S
Institutional support: RVO:67985556
Keywords : benchmark * remote sensing segmentation * unsupervised segmentation * supervised segmentation
Subject RIV: BD - Theory of Information
Impact factor: 2.145, year: 2015
http://library.utia.cas.cz/separaty/2015/RO/haindl-0445995.pdf

We present the enrichment of the Prague Texture Segmentation Data Generator and Benchmark (PTSDB) to include assessment of the remote sensing image segmenters. The PTSDB tool is a web-based (http://mosaic.utia.cas.cz) service designed for real-time performance evaluation, mutual comparison, and ranking of various supervised or unsupervised static or dynamic image segmenters. PTSDB supports rapid verification and development of new segmentation approaches. The remote sensing datasets contain ten-spectral ALI satellite images, their RGB subsets, and very-high-resolution GeoEye RGB images, with optional additive-noise-resistance checking. Alternative setting options allow us to also test scale, rotation or illumination invariance. The meaningfulness of the newly proposed dataset is demonstrated by testing and comparing several remote sensing segmentation algorithms, and showing that the benchmark figures provide a solid framework for the fair and critical comparison among different techniques.
Permanent Link: http://hdl.handle.net/11104/0247991