Automatic classification algorithm of quick bird images in the problem of evaluating of forest completeness

A. Terehov, N. Makarenko, I. Pak

2014

Full text Open access: Gold Metadata (CSL-JSON)

DOI 10.18287/0134-2452-2014-38-3-580-583

Data confidence 70 medium

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Automated technology based on ultra-high spatial resolution (QuickBird) satellite data has been developed to estimate fraction of projective covering by crowns of trees and calculate forest integrity on the sample of Aman-Karagaisky forest in the Northern Kazakhstan. The processing algorithm is based on the threshold allocation of mask of shadows and its succeeding morphological filtering. The map of forest’s test area integrity built by Land Cover Classification System [LCCS] criteria have an accuracy of 82.5% relatively to the corresponding map based on an expert decoding.