Author(s)

A. Tsouchlaraki

Abstract

This study aims to investigate quantitative indices for the automatic evaluation and classification of landscape scenic quality using digital ground photographs. Research efforts to date are scarce on automated extraction of qualitative information based on photographs and therefore this study contributes in this respect, i.e. the automated quantification of landscape scenic quality. Based on the texture indices that are commonly used in landscape ecology, nine quantitative indices are selected to describe the fragmentation and complexity of the landscape, and the results from the application of these indices to a sample of ground photographs are described in this paper. Furthermore, we investigate the effectiveness of the indices selected with respect to the classification of the landscape's scenic quality, while the results are compared to the results derived from a research programme of the National Technical University of Athens. Also, as research experience has shown that texture indices are affected by data resolution, this paper investigates the influence of this factor in the calculation of the quantitative indices that are applied in digital ground photographs. Comments and suggestions for further investigation are presented. The main conclusion of the investigation is that the texture measurement indices are sensitised in the landscape's scenic quality, a fact that is positive and encouraging enough in order to pursue further research.

Keywords

digital ground photographs, fragmentation and complexity measures, geographical information systems, landscape evaluation and classification, landscape scenic beauty, texture indices