Detail publikace

Individual tree crowns delineation using local maxima approach and seeded region growing technique

NOVOTNÝ, J.

Originální název

Individual tree crowns delineation using local maxima approach and seeded region growing technique

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Remote sensing applications in forestry can profit from a rapid development of optical sensors. New hyperspectral sensors have very high spatial and spectral resolution and provide continuous spectral cover in visible and infrared spectral region. Applied algorithms should be suited to the new properties of the data to achieve its maximal advantage. Segmentation of the image into objects is a fundamental task in image processing. It is important in forestry applications of optical remote sensing as well. We are looking for a position of individual tree crowns. Such process traditionally involves two parts: 1) detection and 2) delineation phase. Local maxima approach and seeded region growing technique are presented as the key concepts. Furthermore improvements, namely histogram equalization and Voronoi diagram, are incorporated. Two independent datasets were processed and results of the segmentation are presented. Hyperspectral data with spatial resolution of 0.8m were found as a suitable for segmentation process with 84% and 78% accuracy of detection phase and 64% and 52% accuracy in delineation phase respectively. Finally discussion of recommended settings in the algorithm is provided based on the segmentation results.

Klíčová slova

tree crowns, delineation, seeded region growing technique

Autoři

NOVOTNÝ, J.

Rok RIV

2011

Vydáno

26. 1. 2011

ISBN

978-80-248-2366-9

Kniha

GIS Ostrava 2011

Strany od

49

Strany do

59

Strany počet

10

BibTex

@inproceedings{BUT89039,
  author="Jan {Novotný}",
  title="Individual tree crowns delineation using local maxima approach and seeded region growing technique",
  booktitle="GIS Ostrava 2011",
  year="2011",
  pages="49--59",
  isbn="978-80-248-2366-9"
}