areas, the best results were obtained for the contextual 
classification by increasing the neighbourhood. This leads to a 
stronger smoothing effect. In comparison to a non-contextual 
classification method the results can be significantly improved 
by incorporating information of the neighbouring points. For 
mussel bed areas, the results showed a high number of false 
positive detections for mudflat areas on the border of tideways. 
In these areas, both classes are characterized by similar feature 
values, in particular based on relative height differences and 
curvatures. Nevertheless, our context based approach increased 
the results and eliminated the noisy appearance of mussel bed in 
the Maximum Likelihood Classification results. 
In the future we intend to experiment our approach using larger 
datasets. Moreover, we want to integrate more features to obtain 
a reliable classification by decreasing the number of confusion 
errors for mussel bed and mudflat areas. Therefore, we intend to 
incorporate full waveform laser scanning data as well as some 
texture features. 
6. ACKNOWLEDGEMENT 
We would like to thank the Wadden Sea National Park of 
Lower Saxony, esp. Hubert Farke and Winny Adolph, for 
providing ground truth data. We also thank the Lower Saxon 
State Department for Waterway, Coastal and Nature 
Conservation (NLWKN) for providing the LIDAR data. 
7. REFERENCES 
Anguelov, D., Taskar, B., Chatalbashev, V., Koller, D., Gupta, 
D., Heitz, G. and Ng, A., 2005. Discriminative learning of 
markov random fields for segmentation of 3d scan data. In: 
Proceedings of the 2005 IEEE Computer Society Conference on 
Computer Vision and Pattern Recognition (CVPR'05), Vol. 2, 
IEEE Computer Society, pp. 169—176. 
Brzank, A., Heipke, C., Goepfert, J., Soergel, U., 2008. Aspects 
of generating precise digital terrain models in the Wadden Sea 
from lidar - waterclassification and structure line extraction. In: 
ISPRS Journal of Photogrammetry and Remote Sensing, 63(5), 
pp. 510-528. 
Chehata, N., Guo, L., Mallet, C., 2009. Airborne lidar feature 
selection for urban classification using random forests. In: The 
International Archives of the Photogrammetry, Remote Sensing 
and Spatial Information Sciences, Vol. XXXVIII, Part3/WS8, 
Paris, France, pp. 207-212. 
Frey, B. and MacKay, 1998. A revolution: Belief propagation in 
graphs with cycles. In: Advances in Neural Information 
Processing Systems 10, pp. 479-485. 
Hall, M. A., 1999. Correlation-based Feature Subset Selection 
for Machine Learning. PhD dissertation, Department of 
Computer Science, University of Waikato. 
Hófle, B., Vetter, M., Pfeifer, N., Mandlburger, G., & Stótter, J., 
2009. Water surface mapping from airborne laser scanning 
using signal intensity and elevation data. In: Earth Surface 
Processes and Landforms , 34 (12), pp. 1635-1649. 
Klonus, S., Tomowski, D., Ehlers, M., und Wohlfahrt, R., 2011. 
Potential of Rapideye image data for Wadden Sea monitoring, 
        
   
    
   
   
   
    
  
   
    
    
    
    
   
   
   
    
   
    
   
   
   
   
    
   
    
     
     
     
   
   
   
   
  
  
  
  
   
   
  
   
  
  
Proceedings of 32nd EARSeL Symposium 2011, Prague, CD, 9 
PP. 
Kumar, S. and Hebert, M., 2006. Discriminative Random 
Fields. International Journal of Computer Vision, 68(2), pp. 
179—201. 
Lafferty, J., McCallum, A. and Pereira, F., 2001. Conditional 
random fields: Probabilistic models for segmenting and labeling 
sequence data. In: Proc. [8th International Conference on 
Machine Learning, pp. 282—289. 
Lim EH. and Suter, D.,2009. 3d Terrestrial Lidar 
Classifications with Super-Voxels and Multi-Scale Conditional 
Random Fields. Computer-Aided Design, 41(10), pp. 701-710. 
Liu, D.C. and Nocedal, J., 1989. On the Limited Memory BFGS 
method for large scale optimization. Mathematical 
Programming, 45, pp. 503-528. 
Niemeyer, J., Wegner, J., Mallet, C., Rottensteiner, F. and 
Soergel, U., 2011. Conditional random fields for urban scene 
classification with full waveform lidar data. In: 
Photogrammetric Image Analysis (PIA), Lecture Notes in 
Computer Science, Vol. 6952, Springer Berlin / Heidelberg, pp. 
233-244. 
Schmidt, A.; Rottensteiner, F.; Soergel, U., 2011. Detection of 
Water Surfaces in Full-Waveform Laser Scanning Data. In: 
International Archives of the Photogrammetry, Remote Sensing 
and Spatial Information Sciences, Vol. XXXVIII, Part4/W19, 
Hannover, CD, 6 pp. 
Schmidt, M., 2012. UGM: A Matlab toolbox for probabilistic 
undirected graphical models, http://www.di.ens.fr/-mschmidt 
/Software/UGM html (February 15, 2012). 
Shapovalov, R., Velizhev, A. and Barinova, O., 2010. Non- 
associative Markov Networks for 3d Point Cloud Classification. 
In: Proceedings of the ISPRS Commission III symposium - PCV 
2010, International Archives of the Photogrammetry, Remote 
Sensing and Spatial Information Sciences, 38/Part A, ISPRS, 
Saint-Mandé, France, pp. 103—108. 
WIMO, 2012. Wissenschaftliches Monitoringkonzepte für die 
Deutsche Bucht, hitp:///wimo-nordsee.de (April 10, 2012) 
Witten, LH. and Frank, E., 2005. Data mining: practical 
machine learning tools and techniques, 2nd edition. Morgan 
Kaufmann, San Francisco. 
KEY 
ABS 
Intro 
many 
is aff 
segm 
prope 
Follo 
repre 
point 
smoo 
costs 
an en 
NP k 
maxi 
featu 
well 
simp! 
energ 
1.1. 
Lidai 
most 
geos| 
progi 
rapid 
varie 
and ] 
have 
techr 
beyo 
Appl 
clou 
deriv 
al, 2 
are I; 
the 
acqu 
Scan: 
SMOC 
airbc 
acqu 
For 
unsti 
usua 
is us 
a Wi 
regic 
segn