This paper proposes a visitor counter system which is capable of counting single & multiple object visitors using fuzzy measure theory for tracking and Boosting method for classification. Besides fuzzy measure theory, the paper also uses Euclidean distance to track a visitor based on his movement between each frame, while fuzzy measure theory tracks a visitor based on trust degree. Both system performances are compared for their visitor tracking accuracy and their computational speed. Experimental results show that Euclidean distance and Fuzzy measure have similar accuracy for tracking visitor. However, Euclidean distance is faster than those of fuzzy measure theory in the computational speed. The proposed visitor counter system can be further developed for real-time visitor counting in shopping mall, station, and other places.
|Number of pages||10|
|Journal||WSEAS Transactions on Information Science and Applications|
|Publication status||Published - Jan 2010|
- Boosting classifier
- Euclidean distance
- Fuzzy measure
- Object detection