Segmentation of physiographic features from the global digital elevation model/GTOPO30
Computers & Geosciences
High-resolution landform classification using fuzzy k-means
Fuzzy Sets and Systems - Special issue on Uncertainty in geographic information systems and spatial data
Fuzzy Sets and Systems - Special issue on Uncertainty in geographic information systems and spatial data
Modelling vague places with knowledge from the Web
International Journal of Geographical Information Science - Digital Gazetteer Research
Hi-index | 0.00 |
Methods to automatically derive landforms have typically focused on pixel-based, bottom-up approaches and most commonly on the derivation of to pographic eminences. In this paper we describe an object-based, top-down algo rithm to identify valley floors. The algorithm is based on a region growing ap proach, seeded by thalwegs with pixels added to the region according to a threshold gradient value. Since such landforms are fiatwe compare the results of our algorithm for a particular valley with a number of textual sources de scribing that valley. In a further comparison, we computed a pixel-based six-fold morphometric classification for regions we classified as either being, or not being, valley floor. The regions classified as valley floor are dominated by pla nar slopes and channels, though the algorithm is robust enough to allow local convexities to be classified as within the valley floor. Future work will explore the delineation of valley sides, and thus complete valleys.