yed 
ely 
  
ely 
ore 
ted 
ido 
  
ata 
ido 
5.5 CEST 
The result of the four methods combined in the CEST approach 
is shown in Fig. 7 (right). In comparison to the other methods, 
this image contains far less noise. Also, misclassification of 
vegetation as changed buildings is significantly less. In 
addition, the walls of the buildings are more accurate than for 
the other results. In total, the combination of all three methods 
generates the most reliable and accurate results for change 
detection which is also demonstrated by the accuracy 
assessment. The k-coefficients are presented in table 1. 
  
Fig. 7 Change detection by post classification (left) and CEST 
(right) 
  
  
  
  
  
  
  
Tab. 1 x-coefficients for the change detection methods 
5.6 Damage Map 
For the damage map, the original image of T2 is used as 
background for the automatically created change maps. 
Unchanged areas are transparent, low to moderate changes are 
shown as yellow overlay, and areas of strong changes as red 
overlay. New building areas are shown in green. If this 
technique is applied to areas with catastrophic events, this 
change map makes it possible to quickly identify the most 
affected areas or the areas for which high casualties are likely. 
For the Abu Suruj area, it could be easily depicted that the town 
has increased, but also that large parts of the city have changed. 
Buildings were destroyed and new buildings were built on these 
sites or next to the destroyed buildings (Fig. 8). 
6. CONCLUSIONS 
In this paper, a new automated change detection method 
(CEST) is presented. CEST combines adaptive filtering in the 
frequency domain with edge detection in the spatial domain, 
calculation of the texture features ‘homogeneity’ and ‘energy’ 
with a PCA change detection approach and segment based 
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B7, 2012 
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia 
correlation. This combined method is compared to five standard 
change detection algorithms (image difference, image ratio, 
PCA, delta cue, and post classification analysis). Results are 
visually and quantitatively analyzed. The accuracy assessment 
shows that the CEST method is far superior to the standard 
techniques for change detection. The combined method yields 
an overall accuracy of 80 % and more than 90 % of the 
unchanged buildings could be correctly identified. The method 
is also transferable to other scenes of Darfur. 
  
Fig. 8 Change map of Abu Suruj: new buildings (green), low to 
moderate change (yellow), extensive change (red). 
7. REFERENCES 
Blaschke, T., S. Lang & G. Hay (Eds.), 2008. Object-Based 
Image Analysis — Spatial Concepts for Knowledge-Driven 
Remote Sensing Applications, Springer Lecture Notes in 
Geoinformation and Cartography, Heidelberg. 
Cooley, JW. & JW. Tukey, 1965. Raster algorithm for 
machine calculation of complex Fourier series, Mathematics of 
Computation, vol. 19, 297-301. 
Coppin, P., I. Jonckheere, K. Nackaerts, B. Muys, & E. 
Lambin, 2004. Digital change detection methods in ecosystem 
monitoring a review. International journal of remote sensing, 
2509), pp. 1565-1596. 
Dai, X. & S. Khorram, 1999. Remotely sensed change detection 
based on artificial neural networks, Photogrammetric 
Engineering and Remote Sensing, vol. 65, pp. 1187-1194. 
Ehlers, M & D. Tomowski, 2008. On segment based image 
fusion, in: Blaschke, T., S. Lang and G. Hayes (Eds.), Object- 
Based Image Analysis — Spatial Concepts for Knowledge- 
Driven Remote Sensing Applications, Springer Lecture Notes in 
Geoinformation and Cartography, Heidelberg, pp. 735-754. 
Foody, G.M., 2001. Monitoring the magnitude of land-cover 
change around the southern limits of the Sahara, 
Photogrammetric Engineering and Remote Sensing, vol. 67, pp. 
841-84. 
Haralick, R.M., K. Shanmugam & I. Dinstein, 1973. Textural 
features for image classification, IEEE Trans. Syst, Man, 
Cybern., vol. 3, pp. 610-621.