Naslov
Detecting Forest Damage in CIR Arial Photographs Using a Neural Network

Autori
Klobučar, Damir ; Pernar, Renata ; Lončarić, Sven ; Subašić, Marko ; Seletković, Ante ; Ančić, Mario

Izvornik
Croatian journal of forest engineering (1845-5719) 31 (2010), 2; 157-163

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
forest damage; color infrared aerial photographs; segmentation; neural networks; Croatia

Sažetak
Forest dieback is taking on increasing proportions in many parts of Croatia. To improve the situation, it is of primary importance to acquire timely, accurate and inexpensive information on the scale of forest damage. Such information can be collected for large forest areas with remote sensing techniques. The paper explores the possibility of applying segmentations of colour infrared aerial photographs (CIR). Self-organizing artificial neural networks are used to detect damage in beech-fir forests and determine its spatial distribution. The results of the research confirm the benefits of applying neural networks to forest damage detection, since there are no statistically significant differences between damage in the field and damage detected with a neural network.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Šumarstvo

POVEZANOST RADA