Semi-automated forest stand delineation using wavelet based segmentation of very high resolution optical imagery
Stand delineation is one of the cornerstones of forest inventory mapping and a key element to spatial aspects in forest management decision making. Stands are forest management units with similarity in attributes such as species composition, density, clos
- PDF / 2,243,184 Bytes
- 20 Pages / 439.37 x 666.142 pts Page_size
- 96 Downloads / 217 Views
F.M.B. Van Coillie, L.P.C. Verbeke, R.R. De Wulf Laboratory of Forest Management and Spatial Information Techniques, Ghent University, Belgium, [email protected]
KEYWORDS: Image segmentation, forest stand delineation, wavelets ABSTRACT: Stand delineation is one of the cornerstones of forest inventory mapping and a key element to spatial aspects in forest management decision making. Stands are forest management units with similarity in attributes such as species composition, density, closure, height and age. Stand boundaries are traditionally estimated through subjective visual air photo interpretation. In this paper, an automatic stand delineation method is presented integrating wavelet analysis into the image segmentation process. The new method was developed using simulated forest stands and was subsequently applied to real imagery: scanned aerial photographs of a forest site in Belgium and ADS40 aerial digital data of an olive grove site in Les Beaux de Provence, France. The presented method was qualitatively and quantitatively compared with traditional spectral based segmentation, by assessing its ability to support the creation of pure forest stands and to improve classification performance. A parcel/stand purity index was developed to evaluate stand purity and the expected mapping accuracy was estimated by defining a potential mapping accuracy measure. Results showed that wavelet based image segmentation outperformed traditional segmentation. Multi-level wavelet analysis proved to be a valuable tool for characterizing local variability in image texture and therefore allowed for the discrimination between stands. In addition, the proposed evaluation measures were found appropriate as segmentation evaluation criteria.
238
F.M.B. Van Coillie, L.P.C. Verbeke, R.R. De Wulf
1 Introduction Forest stands are the basic units of management and are generally defined as spatially continuous units of uniform species composition, stem density, crown closure, height and age (Leckie et al. 2003). Correct tree species identification for example is essential for forest management and in applications such as species-specific growth models. The calculation of timber volumes is also usually species specific. Traditionally stand boundaries have been estimated through air photo interpretation. Visual interpretation however is subjective and can be ameliorated by numerical interpretation through automated image processing (Haara and Haarala 2002, Wulder et al. 2007). New mapping techniques are subject of research in terms of improved speed, consistency, accuracy, level of detail and overall effectiveness (Leckie et al. 2003). Several techniques have been developed but most of them are designed for automated tree isolation e.g. Gougeon (1995a,b), Culvenor (2002), Larsen (1997) and Warner et al. (1998). Subsequent stand delineation based on individually outlined trees is less developed but has been extensively studied by Leckie et al. (2003). Another possibility is the automatic delineation of stands based on image segme
Data Loading...
