Title :
Automatic Segmentation and Tracking of Objects in Videocomputer System
Author :
Oboukhova, Natalia A.
Author_Institution :
St. Petersburg State Univ.
Abstract :
The automatic segmentation algorithm for many objects of interest on the basis of the mathematical technique of fuzzy logic is considered The features and belonging functions of blocks to clusters on the initial segmentation stage with unknown number of clusters are considered. The technique of objects characteristics definition (gravity centers, form parameters and movement models) is given. The attributes and belonging functions of blocks to objects during tracking are determined. The resolution for situation occlusion (overlapping of objects) is shown
Keywords :
fuzzy logic; image resolution; image segmentation; mathematical analysis; tracking; video signal processing; automatic segmentation algorithm; fuzzy logic; image resolution; mathematical technique; object tracking; occlusion; videocomputer system; Clustering algorithms; Frequency estimation; Fuzzy logic; Gravity; Image motion analysis; Image segmentation; Motion estimation; Object segmentation; Tracking; Wavelet analysis; Automatic segmentation; belonging function; feature of detail; feature of form; feature of movement; fuzzy logic; motion vectors; occlusion; optical flow; tracking;
Conference_Titel :
Consumer Electronics, 2006. ISCE '06. 2006 IEEE Tenth International Symposium on
Conference_Location :
St. Petersburg
Print_ISBN :
1-4244-0216-6
DOI :
10.1109/ISCE.2006.1689479
