Title :
Fuzzy representation and grouping in building detection
Author :
Levitt, Stephen ; Aghdasi, Farzin
Author_Institution :
Dept. of Electr. Eng., Witwatersrand Univ., South Africa
Abstract :
We present a novel fuzzy approach for the task of detecting buildings in monocular greyscale imagery in the form of our system FuzzBuRS. Our approach rigorously addresses the problem of uncertainty and imprecision that exists within the building recognition scenario. Fuzzy variables are used for representing various types of building evidence, such as significant straight edges and homogeneous regions. These variables and fuzzy if/then rules allow for a fuzzy reasoning system that assigns possibilities to building hypotheses. FuzzBuRS demonstrates the potential of a fuzzy approach to the building recognition task. This system has a compact representation and is easily understandable
Keywords :
fuzzy logic; inference mechanisms; object detection; object recognition; uncertainty handling; FuzzBuRS system; building detection; building hypotheses; building recognition; compact representation system; fuzzy grouping; fuzzy if/then rules; fuzzy reasoning system; fuzzy representation; fuzzy variables; homogeneous regions; imprecision problem; monocular greyscale imagery; straight edges; uncertainty problem; Africa; Computer vision; Feature extraction; Fuzzy reasoning; Fuzzy systems; Image databases; Image edge detection; Image reconstruction; Spatial databases; Uncertainty;
Conference_Titel :
Image Processing, 2000. Proceedings. 2000 International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-6297-7
DOI :
10.1109/ICIP.2000.899377
