Forest tree species clssification based on airborne hyper-spectral imagery

Forest precision classification products were the basic data for surveying of forest resource, updating forest subplot information, logging and design of forest. However, due to the diversity of stand structure, complexity of the forest growth environment, it's difficult to discriminate forest tree species using multi-spectral image. The airborne hyperspectral images can achieve the high spatial and spectral resolution imagery of forest canopy, so it will good for tree species level classification. The aim of this paper was to test the effective of combining spatial and spectral features in airborne hyper-spectral image classification. The CASI hyper spectral image data were acquired from Liangshui natural reserves area. Firstly, we use the MNF (minimum noise fraction) transform method for to reduce the hyperspectral image dimensionality and highlighting variation. And secondly, we use the grey level co-occurrence matrix (GLCM) to extract the texture features of forest tree canopy from the hyper-spectral image, and thirdly we fused the texture and the spectral features of forest canopy to classify the trees species using support vector machine (SVM) with different kernel functions. The results showed that when using the SVM classifier, MNF and texture-based features combined with linear kernel function can achieve the best overall accuracy which was 85.92%. It was also confirm that combine the spatial and spectral information can improve the accuracy of tree species classification.

[1]  A. Skidmore,et al.  A hyperspectral band selector for plant species discrimination , 2007 .

[2]  Dengsheng Lu,et al.  Integration of vegetation inventory data and Landsat TM image for vegetation classification in the western Brazilian Amazon , 2005 .

[3]  J. J. Colls,et al.  Use of hyperspectral derivative ratios in the red-edge region to identify plant stress responses to gas leaks , 2004 .

[4]  Gregory Asner,et al.  Applications of Remote Sensing to Alien Invasive Plant Studies , 2009, Sensors.

[5]  J. Qi,et al.  A comparative analysis of broadband and narrowband derived vegetation indices in predicting LAI and CCD of a cotton canopy , 2007 .

[6]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[7]  V. V. Kozoderov,et al.  Remote sensing of soils and vegetation: quantitative parameters retrieval using pattern-recognition techniques and forest stand structure assessment , 2011 .

[8]  Kai Wang,et al.  Remote Sensing of Ecology, Biodiversity and Conservation: A Review from the Perspective of Remote Sensing Specialists , 2010, Sensors.

[9]  Alexandre Jouan.  FastICA(MNF) for feature generation in hyperspectral imagery , 2007, 2007 10th International Conference on Information Fusion.

[10]  Validation of Statistic Based Forest Types Classification Methods Using Hyperspectral Data , 2007 .

[11]  N. Mizoue,et al.  Classifying tropical deciduous vegetation: a comparison of multiple approaches in Popa Mountain Park, Myanmar , 2011 .

[12]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[13]  Susan L. Ustin,et al.  Identification of invasive vegetation using hyperspectral remote sensing in the California Delta ecosystem , 2008 .

[14]  Susan L Ustin,et al.  Remote sensing of plant functional types. , 2010, The New phytologist.

[15]  Peter Bajorski,et al.  Statistical Inference in PCA for Hyperspectral Images , 2011, IEEE Journal of Selected Topics in Signal Processing.

[16]  D. Roberts,et al.  Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales , 2005 .

[17]  David A. Landgrebe,et al.  Classification of remote sensing images having high spectral resolution , 1996 .

[18]  Peng Gong,et al.  Land cover assessment with MODIS imagery in southern African Miombo ecosystems , 2005 .

[19]  M. Batistella,et al.  A Comparative Study of Landsat TM and SPOT HRG Images for Vegetation Classification in the Brazilian Amazon. , 2008, Photogrammetric engineering and remote sensing.