Abstract: Building height information extraction is one of the hot issues in urban spatial information 
acquisition by high-resolution satellite remote sensing. An object-oriented building height 
retrieval method based on the rules of the information is proposed in this work in order to 
extract building height information accurately. Firstly, the building shadow extraction 
algorithm based on rule information was established according to the building shadow geometry, 
texture and spectral characteristics, and building shadow information was extracted.  Then the 
length of the shadow was  calculated by computing the average value of pixels, and the building 
height was inverted by using the spatial model of satellite, the sun, the building and its shadow.  
Two building height retrieval experiments was carried out based on GF-2 satellite remote 
sensing data of the two experimental area of Yangzhou (Jiajia garden and Shanwan community).  
Through the actual height measurement of 105 buildings, the retrieval results are verified 
and the overall accuracy is 96.5%. It shows that the method has high precision in the aspect 
of city building height information extraction.

Key words: GF-2 satellite, rule-based information, shadow length, building height