Chen Yuen Teoh 
  
  
(a) Original Image (b) Preprocessed Image 
Figure 5: Original and Preprocessed Test Image 
(a) Input Image (b) Supervised Learning Out- (c) Clustering Output 
put 
Figure 6: Input/Output at Junction Recognition Level 
In the future, we hope to gather more examples to allow more experiments to be carried out. This will help us to sharpen 
our rules for extraction and produce better extraction results. Finally, we need to integrate the results from the junction 
recognition level with the previous level output, the linked road segments, to form a complete road image. 
REFERENCES 
Baumgartner, A., Extraction of Roads from Aerial Imagery Based on Grouping and Local Context, in: International Archives of 
Photogrammetry and Remote Sensing (1998), Volume XXXII, Part 3-3/1, pp. 196-201. 
Baumgartner, A., Steger, C., Wiedemann, C., Mayer, H., Eckstein, W., Ebner, H., Update of Roads in GIS from Aerial Imagery: 
Verification and Multi-Resolution Extractio, in: International Archives of Photogrammetry and Remote Sensing, vol XXXI, part B3, 
1996. 
Cleynenbreugel, J. V., Osinnga, S. A., Fierens, F., Suetens, P., Oosterlinck, A., Road Extraction From Multi-Temporal Satellite Images 
by an Evidential Reasoning Approach, in: Elsevier Science Publishers B.V. (North-Holland), June 1991, pp. 371-380. 
De Gunst, M., Knowledge-based interpretation of aerial images for updating of road maps, in: Netherlands Geodetic Commission, 
Publication of Geodesy, New Series No. 44, 1996. 
Dillon, G.. Caelli, T., Cite: A Scene Understanding and Object Recognition System, in: ACCV'95 Second Asian Conference on 
Computer Vision, December 5-8, 1995, pp. I-214-I-218. 
Duda, R. O. and Hart, P. E., Pattern Classification and Scene Analysis, Wiley, New York, 1973. 
Gruen, A.. Li, H., Semi-Automatic Linear Feature Extraction by Dynamic Programming and LSB-Snakes, in: Photogrammetric Engi- 
neering and Remote Sensing (PE&RS), Vol 63, No. 8, August 1997, pp. 985-995. 
Huang. X., Jensen. J., Mackey, H. E., Jr., A Machine Learning Approach to Automated Construction of Knowledge Based for Expert 
Systems for Remote Sensing Image Analysis with GIS Data, in: GIS/LIS 1995 Annual Conference and Exposition, pp.456-465. 
Liedtke, C. E., Buuckner, J., Grau, O., Growe, S., Tójes, R., AIDA: A System for the Knowledge Based Interpretation of Remote Sensing 
Data, Presented at the Third International Airborne Remote Sensing Conference and Exhibition, 7-10 July 1997. 
  
International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B3. Amsterdam 2000. 887