Title :
Image moments-based structuring and tracking of objects
Author :
Rocha, Lourena ; Velho, Luiz ; Carvalho, Paulo Cezar P
Author_Institution :
Instituto Nacional de Matematica Pura e Aplicada, Rio de Janeiro, Brazil
Abstract :
This paper presents a new method for structuring and tracking of objects in video sequences. Our approach is based on image moments and the BSP-tree data structure. We use invariant properties of these moments to construct a BSP-tree and determine an ellipsis that approximates the object´s shape. Then, we employ this information to track objects frame by frame through the image sequence. The method works well for segmented images with a single object and we assume that the motion will not change abruptly.
Keywords :
image sequences; object detection; optical tracking; tree data structures; video signal processing; BSP-tree data structure; ellipsis; image moments-based object structuring; image moments-based object tracking; invariant properties; segmented images; video sequences; Active contours; Data structures; Ellipsoids; Image motion analysis; Image segmentation; Image sequences; Robustness; Shape; Target tracking; Video sequences;
Conference_Titel :
Computer Graphics and Image Processing, 2002. Proceedings. XV Brazilian Symposium on
Print_ISBN :
0-7695-1846-X
DOI :
10.1109/SIBGRA.2002.1167130
