Title :
Detecting automobiles and people for semantic video retrieval
Author :
Visser, Rene ; Sebe, Nicu ; Lew, Michael S.
Author_Institution :
LIACS Media Lab, Leiden Univ., Netherlands
Abstract :
This paper describes a method for detecting automobiles and people in streaming or archived video. Our video object tracking system is based on Kalman filter updating of an active contour over the video sequence. We use the sequential probability ratio test (SPRT) to classify the moving objects. Results are shown of a real video sequence from a busy city intersection.
Keywords :
Kalman filters; image classification; image motion analysis; image segmentation; image sequences; object detection; probability; video signal processing; Kalman filter updating; active contour; archived video; automobile detection; busy city intersection; image sequence analysis; moving object classification; moving object segmentation; people detection; semantic video retrieval; sequential probability ratio test; streaming video; video object tracking system; video sequence; Automobiles; Face detection; Image segmentation; Kalman filters; Layout; Object detection; Sequential analysis; Streaming media; Testing; Video sequences;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1048407
