Object based forest stand density estimation from very high resolution optical imagery using wavelet based texture measures

Stand density or tree density, expressed as the number of trees per unit area, is an important forest management parameter. It is used by foresters to evaluate regeneration, to assess the effect of forest management measures or as an indicator variable for other stand parameters like age, basal area and volume. A stand density estimation technique, based on the application of wavelet analysis, is presented in this work. First, very high resolution imagery is segmented using a wavelet based segmentation algorithm. Then, wavelet coefficient statistics are calculated for each separate object in order to characterize local texture. Next, the wavelet statistics are related to stand density using an artificial neural network. The established relation is finally used to produce semi-continuous stand density maps. In order to test the proposed method, several color-infrared aerial photographs (scale 1:5000) were scanned, mosaiced and converted to 25cm resolution orthophotos. A large number of trees (45,000) were manually digitized on this dataset. The available imagery was degraded to 1m and 2m spatial resolutions, and the new algorithm was applied. To put the presented method in perspective, a comparison was made with the local maximum filter, a conventional density estimation and individual tree identification method. Analysis of variance revealed that the wavelet based technique performed significantly better (p < 0.001) when compared with the local maximum based method, in terms of correlation, root mean square error and mean absolute difference, regardless of resolution or spectral band.

[1]  Lieven Verbeke,et al.  Semi-automated forest stand delineation using wavelet based segmentation of very high resolution optical imagery , 2006 .

[2]  F. Gougeon.  A Crown-Following Approach to the Automatic Delineation of Individual Tree Crowns in High Spatial Resolution Aerial Images , 1995 .

[3]  P. Gong,et al.  Wavelet transform applied to EO-1 hyperspectral data for forest LAI and crown closure mapping , 2004 .

[4]  Joanne C. White,et al.  Comparison of airborne and satellite high spatial resolution data for the identification of individual trees with local maxima filtering , 2004 .

[5]  K. O. Niemann,et al.  Local Maximum Filtering for the Extraction of Tree Locations and Basal Area from High Spatial Resolution Imagery , 2000 .

[6]  B. St-Onge,et al.  Estimating forest stand structure from high resolution imagery using the directional variogram , 1995 .

[7]  L. Wald,et al.  Fusion of high spatial and spectral resolution images : The ARSIS concept and its implementation , 2000 .

[8]  F. M. Danson,et al.  Satellite remote sensing of forest resources: three decades of research development , 2005 .

[9]  J. H. Park,et al.  Spatially adaptive multi-resolution multispectral image fusion , 2004 .

[10]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[11]  Frédéric Achard,et al.  A novel approach to the classification of regional-scale Radar mosaics for tropical vegetation mapping , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Hampus Holmström,et al.  Estimation of single-tree characteristics using the kNN method and plotwise aerial photograph interpretations , 2002 .

[13]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[14]  Sassan Saatchi,et al.  The use of decision tree and multiscale texture for classification of JERS-1 SAR data over tropical forest , 2000, IEEE Trans. Geosci. Remote. Sens..

[15]  Rob J. Dekker,et al.  Texture analysis and classification of ERS SAR images for map updating of urban areas in The Netherlands , 2003, IEEE Trans. Geosci. Remote. Sens..

[16]  Michael A. Wulder,et al.  Optical remote-sensing techniques for the assessment of forest inventory and biophysical parameters , 1998 .

[17]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[18]  Jean-Philippe Gastellu-Etchegorry,et al.  Recovery of forest canopy characteristics through inversion of a complex 3D model , 2002 .

[19]  K. Olaf Niemann,et al.  Error reduction methods for local maximum filtering of high spatial resolution imagery for locating trees , 2002 .

[20]  B. St-Onge.  Automated forest structure mapping from high resolution imagery based on directional semivariogram estimates , 1997 .

[21]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[22]  Lindi J. Quackenbush,et al.  Developing Forestry Products from High Resolution Digital Aerial Imagery , 2000 .

[23]  Stuart R. Phinn,et al.  Determining forest structural attributes using an inverted geometric-optical model in mixed Eucalypt , 2000 .

[24]  Barry Boots,et al.  Techniques for accuracy assessment of tree locations extracted from remotely sensed imagery. , 2005, Journal of environmental management.

[25]  G. Edwards,et al.  Automated estimation of localized forest volume from large-scale aerial photographs and ancillary cartographic information in a boreal forest , 1999 .

[26]  Jiang Li,et al.  Correction to "Wavelet-Based Feature Extraction for Improved Endmember Abundance Estimation in Linear Unmixing of Hyperspectral Signals" , 2004 .

[27]  Limin Yang,et al.  Oblique striping removal in remote sensing imagery based on wavelet transform , 2006 .