Color- and Texture-Based Image Segmentation for Improved Forest Delineation

This paper concentrates on the delineation of forest boundaries from aerial images with focus on spatially contiguous and reproducible results for the Swiss National Forest Inventory. Because of the poor performance of common edge models to extract natural vegetation boundaries, this paper presents a combined method of image segmentation and wavelet-based texture features for the delineation of forest. The selected -measure-based segmentation method has been found to be useful to produce initial segmentation results, but lacks a semantic concept for forest vegetation. To overcome this conceptual limitation, the combination with wavelet transformation gives access to additional texture features and leads to a robust approach to obtain proper forest boundaries. Preliminary results are encouraging regarding the better agreement compared with maximum-likelihood classification results.

[1]  E. Wald,et al.  Schweizerisches Landesforstinventar : Ergebnisse der Zweitaufnahme 1993-1995 , 1999 .

[2]  Matti Pietikäinen,et al.  Color Texture Classification with Color Histograms and Local Binary Patterns , 2002 .

[3]  B. S. Manjunath,et al.  Rotation-invariant texture classification using a complete space-frequency model , 1999, IEEE Trans. Image Process..

[4]  Jing Li Wang,et al.  Color image segmentation: advances and prospects , 2001, Pattern Recognit..

[5]  Arivazhagan Selvaraj,et al.  Texture segmentation using wavelet transform , 2003, Pattern Recognit. Lett..

[6]  A. Pekkarinen,et al.  A method for the segmentation of very high spatial resolution images of forested landscapes , 2002 .

[7]  J. Liira,et al.  Issues related to delineation of forest boundaries on Landsat Thematic Mapper winter images , 2004 .

[8]  Sankar K. Pal,et al.  A review on image segmentation techniques , 1993, Pattern Recognit..

[9]  D. Leckie.  Stand delineation and composition estimation using semi-automated individual tree crown analysis , 2003 .

[10]  C. Justice,et al.  Global land cover classification by remote sensing: present capabilities and future possibilities , 1991 .

[11]  Michael Unser,et al.  Texture classification and segmentation using wavelet frames , 1995, IEEE Trans. Image Process..

[12]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Heike Lischke,et al.  Swiss National Forest Inventory: Methods and Models of the Second Assessment , 2001 .

[14]  W. Cohen,et al.  An evaluation of alternate remote sensing products for forest inventory, monitoring, and mapping of Douglas-fir forests in western Oregon , 2001 .

[15]  B. S. Manjunath,et al.  Unsupervised Segmentation of Color-Texture Regions in Images and Video , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Nicolai Petkov,et al.  Comparison of texture features based on Gabor filters , 2002, IEEE Trans. Image Process..

[17]  Carolyn T. Hunsaker,et al.  Spatial uncertainty in ecology : implications for remote sensing and GIS applications , 2002 .

[18]  L. Waser,et al.  Combining remotely sensed spectral data and digital surface models for fine-scale modelling of mire ecosystems , 2004 .

[19]  C.-C. Jay Kuo,et al.  Texture analysis and classification with tree-structured wavelet transform , 1993, IEEE Trans. Image Process..

[20]  Hansheinrich Bachofen,et al.  Schweizerisches Landesforstinventar : Ergebnisse der Erstaufnahme 1982-1986 , 1988 .

[21]  J. Hyyppä,et al.  Accuracy comparison of various remote sensing data sources in the retrieval of forest stand attributes , 2000 .

[22]  Andrew O. Finley,et al.  Delineation of forest/nonforest land use classes using nearest neighbor methods , 2004 .

[23]  B. S. Manjunath,et al.  Peer group filtering and perceptual color image quantization , 1999, ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349).

[24]  Majid Mirmehdi,et al.  Segmentation of Color Textures , 2000, IEEE Trans. Pattern Anal. Mach. Intell..