A. Al-Hamadi, R. Niese, and B. Michaelis (Germany)
Segmentation, Tracking, Application
Automatic contour extraction of moving objects and ro bust tracking under disturbed image situations are diffi cult problems in the image sequence analysis. In this pa per, we propose a technique for the automatic contour extraction (object segmentation) and tracking of moving objects in video sequences that works robustly under the influence of non-cooperative measurement situations (e.g. shadow). For this technique, we apply a modified differ ence image-based approach in conjunction with morpho logical, separation and smoothing operators. The ex tracted image regions represent the object candidates for the following tracking. The efficiency of this suggested technology will be demonstrated on the basis of the analysis of strongly disturbed image sequences.
Important Links:
Go Back
