Object-Based Classification of UltraCamD Imagery for Identification of Tree Species in the Mixed Planted Forest

This study is a contribution to assess the high resolution digital aerial imagery for semi-automatic analysis of tree species identification. To maximize the benefit of such data, the object-based classification was conducted in a mixed forest plantation. Two subsets of an UltraCam D image were geometrically corrected using aero-triangulation method. Some appropriate transformations were performed and utilized. Segmentation was conducted stepwise at two levels and a hierarchical image object network was constructed. The classification hierarchy was developed and Nearest Neighbor classifier, using integration of different features was performed. Training samples and ground truth map were prepared through fieldwork. Accuracy assessment of the resulting maps in comparison with reference data showed overall accuracies and Kappa Index of Agreement of 90.2%, 0.82 (Area1) and 69.8%, 0.49 (Area2), respectively. Transformed images were advantageous to improve the results. The lower accuracy in Area2 can be attributed to high diversity and heterogeneous mixture of species. More detailed and accurate mapping of tree species would be fulfilled applying precise 3D data. The accuracy of detailed vegetation classification with very high-resolution imagery is highly dependent on the segmentation quality, sample size, sampling quality, classification framework and ground vegetation distribution and mixture.
 
REFERENCES
Baltsavias, E. Eisenbeiss, H. Akca, D. Waser, L.T. Kuckler, M. Ginzler, C. and Thee, P. (2007) Modeling fractional shrub/tree cover and multitemporal changes using high-resolution digital surface model and CIR-aerial images, URL: http://www.photogrammetry.ethz.ch / general/persons/devrim-pub1.html
Baatz, M. and Schape, A. (1999) Objectoriented and multi-scale image analysis in semantic network, Proc. Of 2nd Int. Symposium on operalization of remote sensing, August 16-20,
Ensched, ITC. Benz, U.C. Hoffmann, P. Willhauck, G. Lingenfelder, I. and Heynen, M. (2004) Multi-resolution Object-oriented Fuzzy analysis of Remote Sensing Data for GIS-ready Information. ISPRS Journal of Photogrammetry and Remote Sensing, 58: 239-258.
Bohlin, J. Olsson, H. Olofsson, K. and Wallerman, J. (2007) Tree species discrimination by aid of template matching applied to digital air photos, URL: http://www.rali.boku.ac.at/ fileadmin/-/H857- VFL/workshops/3drsforestry/ presentations/7.4- Olsson.pdf
Chang, A. Kim, J.O. Ryu, K. and Kim, Y. (2008) Comparison of methods to estimate individual tree attributes using color aerial photographs and LiDAR data, WSEAS Transactions on Signal Processing, 4(1): 21-27.
Congalton, R.G. (1991) A review of assessing the accuracy of classification of remotely sensed data, Remote Sensing of Environment, 37: 35-46.
Definiens (2006) Definiens Professional 5 User Guide, Definiens AG, München, Germany, URL: http//:www.definiens.com.
Delaplacea, K.L.W. Van Coillie F.M.B. De Wulf R.R. Gabriels D. De Smet K. Ouessar M. Ouled Belgacem A. and Houcine T. (2010) Object-based assessment of tree attributes of Acacia tortilis in Bou-Hedma, Tunisia, Proc. of GEOBIA 2010, Ghent, Belgium, URL: http://www.geobia.ugent.be.
Farzaneh, A. (2004) Landcover mapping employing fusion of remotely sensed high-spatial resolution pan and medium-spatial resolution multispectral images in the region of SariIran, PhD Dissertation, Vienna, Austria.
Gong, P. and Howarth, P.J. (1989) Performance analyses of probabilistic relaxation methods for land cover classification, Remote Sensing of Environment, 30: 33-42.
Gong, P. Marceau, D.J. and Howarth, P.J. (1992) A comparison of spatial featureextraction algorithms for land-use classification with SPOT HRV data, Remote Sensing of Environment, 40: 137-151.
Hill, R.A. and Foody, G.M. (1994) Separability of tropical rain forest types in the Tombopata-Candamo reserved zone, Peru, International Journal of Remote Sensing, 15: 2687-2693.
Hirschmugl, M. Ofner, M. Raggam, J. and Schardt, M. (2007) Single tree detection in very high resolution remote sensing data, URL: http://www.sciencedirect.com
Hodgson, M.E. (1998) What size window for image classification? Cognitive perspective, Photogrammetric Engineering & Remote Sensing, 64: 797-807.
Hoover, A. (1996) An experimental comparison range image segmentation algorithms, IEEE Transactions on Pattern Analysis and Machine Intelligence, 18: 673-689.
Levine, M.D. and Nazif, A.M. (1985) Dynamic measurement of computer generated image segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 7: 570-585.
Lillesand, T. and Kiefer, R. (2000) Remote sensing and image interpretation, New York, USA: John Wiley & Sons.
 Loecherbach T. and Thurgood, J.D. (2008) Practical experiences in Photogammetric Production with Digital Frame Camera Imagery, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B4. Beijing, pp. 1865- 1870.
Millette, T.L. and Hayward, C.D. (2004) Detailed forest stand metrics taken from AIMS-1sensor data, URL: http://www.mtholyoke.edu/dept/ea rth/facilities/Millette-b.pdf
Naesset, E. and Gobakken, T. (2005) Estimating forest growth using canopy metrics derived from airborn laser  scanner data, Remote sensing of environment, 96: 453-465.
Neumann, K. (2005) New technology–new possibilities of digital mapping cameras, ASPRS annual conferences, Baltimore, Maryland, 7-11 March.
Ozdemir, I. Norton, D. Ozkan, U.Y. Mert, A. and Senturk, O. (2008) Estimation of tree size diversity using object– oriented texture analysis and ASTER imagery, sensors, 8:4709-4724, URL: http://www.mdpi.org/sensors
Rafieyan, O. Darvishsefat, A.A. Babaii, S. (2009) Evaluation of object-based classification method in forest applications using UltraCamD imagery (Case study: Northern forest of Iran), Proc. of 3^rd National Forest Conference, University of Tehran, Karaj, Iran.
Schiewe, J. (2002) Segmentation of highresolution remotely sensed data, concepts, application and problems, Symposium on geospatial theory, processing and applications, Ottawa, Canada.
Shackelford, A.K. and Davis, C.H. (2003) A hierarchical fuzzy classification approach for high-resolution multispectral data over urban areas, IEEE Transaction on Geoscience and Remote Sensing, 41: 1920-1932.
Shataee S. Kellenberger, T. and Darvishsefat, A.A. (2004) Forest types classification using ETM+ data in the North of Iran/comparison of objectoriented with pixel-based classification techniques, XXth ISPRS Congress, Istanbul, Turkey.
Sohrabi, H. (2009) Visual and digital interpretation of UltraCamD in forest inventory, PhD thesis, Natural resources faculty, Tarbiat Modares University, Nur, Iran.
Voss, M. and Sugumaran, R. (2008) Seasonal effect on tree species classification in an urban environment using hyper-spectral data, LiDAR, and an object-oriented approach, Sensors, 8: 3020-3036.
Wang, Z. Boesch, R. and Ginzler, C. (2008) Integration of high resolution aerial images and airborne LiDAR data for forest delineation, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B7. Beijing, China.
Yu, Q. Gong, P. Clinton, N. Biging, G. Kelly, M. and Schirokauer, D. (2006) Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery, Photogrammetric Engineering & Remote Sensing, 72: 799-811
Zhang, Y. (1996) A survey on evaluation methods for image segmentation, Pattern Recognition, 29: 1334-1346.