third area 
classified as 
; blue) 
lassified as 
s blue) 
  
Figure 9 shows the generated true ortho-photo for the third 
area, and Figure 10 illustrates the classification results of the 
buildings class for the third area. Figure 11 depicts the 
classification results of the trees class for the third area. 
Table 1 gives the classification results of the buildings class 
for the three areas. The buildings misclassifications are 
noticed for objects under our proposed threshold for the 
minimum building area (10 m°). Building parts under the 
ground level was also misclassified as our assumption is that 
buildings extend only above the ground. One building that is 
highly surrounded by vegetation was also misclassified. In 
most of the cases, the RMS of the extracted boundaries and 
the RMS of the coordinates of center of gravity of extracted 
buildings are less than or equal to the corresponding RMS of 
the reference data. 
  
    
Per Area - 
  
  
  
  
  
  
completeness 89.1% 932% | 87.0% 
correctness 94.7% 954% | 952% 
quality 84.8% 89.2% | 83.4% 
Per Object 
ope balanced by 99 494 994% | 91.1% 
Sonesta balanced by 100% 100% 100% 
  
quality balanced by area 99.4% 99.4% | 91.1% 
Boundary Accuracy (m) 
  
  
  
  
  
  
  
  
  
  
RMS of extracted 0.77 0.73 0.54 
boundaries 
RMS of reference 0.94 0.60 0.66 
boundaries 
RMS of centers of gravity 1.21 0.52 0.23 
of extracted objects (x.y) 0.97 0.26 0.36 
RMS of centers of gravity 1.32 0.52 0.23 
of reference objects (x,y) 1.18 0.26 0.36 
  
Table 1. Classification results for the buildings class 
  
  
  
  
  
  
  
Er: ic: 
Per Area 
completeness 37.2% 914% | 83.8% 
correctness 80.1% 60.7% | 58.6% 
quality 34.0% 574% | 52.7% 
Per Object 
1 
Sve eteness balanced by 42.3% 98.5% | 94.2% 
t 
re balanced by 86.0% | 76.1% | 68.0% 
  
quality balanced by area 39.6% 75.3% | 653% 
Boundary Accuracy (m) 
  
  
  
  
  
  
  
  
  
  
RMS of extracted 
boundaries 1.09 1.05 0.88 
RMS of reference 
boundaries 1.38 1.50 1.43 
RMS of centers of gravity 1.06 0.67 0.95 
of extracted objects (x,y) 1.07 0.90 0.78 
RMS of centers of gravity 0.92 0.79 1.17 
of reference objects (x,y) 1.05 1.10 1.01 
  
Table 2. Classification results for the trees class 
    
    
     
   
    
   
  
    
   
    
   
  
      
    
     
     
   
  
   
   
    
   
   
    
   
   
    
    
   
    
    
   
   
    
   
    
    
   
    
   
  
  
    
Table 2 gives the classification results of the trees class for the 
three areas. The reference data assumed trees to be of ideal 
circular shape. The proposed approach does not take this 
assumption into consideration and only considers the true 
boundary of trees based on LIDAR data which affects the 
classification results. In most of the cases, the RMS of the 
extracted boundaries and the RMS of the coordinates of center 
of gravity of extracted objects are less than or equal to the 
corresponding RMS of the reference data. 
4. CONCLUSIONS 
In this research, an object based classification approach has 
been presented that fuse both aerial imagery and LIDAR data. 
This object based analysis enabled a rule based classification 
where the decisions are based on clear and interpretable rules 
related to the scene parameters such as minimum building 
height and minimum building area. In the proposed approach, 
the classification has been performed on two phases where the 
first classification results help to provide the second phase with 
derived feature to help improve the classification accuracy. This 
iterative classification scheme could be further expanded to 
include more features based on the previous successive 
classification phases. The used thresholds are interpretable and 
could be easily changed to match the underlying scene for better 
classification results. The proposed classification rules are 
expandable to include more classes without reconstruction of 
the classifier from scratch. The achieved classification results 
show the significance of the proposed approach. 
ACKNOWLEDGEMENTS 
The Vaihingen data set was provided by the German Society for 
Photogrammetry, Remote Sensing and Geoinformation (DGPF) 
(Cramer, 2010): http://www.ifp.uni-stuttgart.de/dgpf/DKEP- 
Allg.html (in German). 
REFERENCES 
Aplin, P., Atkinson, P.M. and Curran, P.J., 1999. Fine spatial 
resolution simulated satellite imagery for land cover mapping in 
the UK. Remote Sensing of Environment, 68, pp. 206-216. 
Aplin, P., Smith, G.M., 2008. Advances in Object Based Image 
Classification, The International | Archives of the 
Photogrammetry, Remote Sensing and Spatial Information 
Sciences. Vol. XXXVII. Part B7. Beijing. 
Axelsson, P., 2000. DEM generation form laser scanner data 
using adaptive TIN models. The International Archives of the 
Photogrammetry, Remote Sensing and Spatial Information 
Sciences., 33(B4/1), pp. 110—117. 
Baik, S.W., Baik, R., 2004. Adaptive image classification for 
aerial photo image retrieval. 17th Australian Joint Conference 
on Artificial Intelligence, Proceedings, 3339, pp. 132-139. 
Brovelli, M. A., Cannata, M. and Longoni, U.M., 2002. 
Managing and processing LiDAR data within GRASS. Proc. 
GRASS Users Conference, Trento, Italy, 11 — 13 September. 
University of Trento, Italy.