Original scientific paper

Detecting Forest Damage in Cir Aerial Photographs Using a Neural Network

Damir Klobučar ; »Hrvatske šume« d. o. o. Zagreb, Headquaters Zagreb, CROATIA
Renata Pernar ; Forestry Faculty of Zagreb University, Department of Forest Management and Remote Sensing, CROATIA
Sven Lončarić ; University of Zagreb, Faculty of Electrical Engineering and Computing, Department of Electronic Systems and Information Processing, CROATIA
Marko Subašić ; University of Zagreb, Faculty of Electrical Engineering and Computing, Department of Electronic Systems and Information Processing, CROATIA
Ante Seletković ; Forestry Faculty of Zagreb University, Department of Forest Management and Remote Sensing, CROATIA
Mario Ančić ; Forestry Faculty of Zagreb University, Department of Forest Management and Remote Sensing, CROATIA

Abstract

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. This paper explores the possibility of applying segmentations of color 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.

Keywords

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

Hrčak ID:

63726

URI

https://hrcak.srce.hr/63726

Publication date:

20.12.2010.

Visits: 1.969 *