Title :
Spatiotemporal visual attention architecture for video analysis
Author :
Rapantzikos, Konstantinos ; Tsapatsoulis, Nicolas ; Avrithis, Yannis
Author_Institution :
Sch. of Electr. & Comput. Eng., Nat. Tech. Univ. of Athens, Greece
fDate :
29 Sept.-1 Oct. 2004
Abstract :
Several visual attention (VA) schemes have been proposed with the saliency-based ones being the most popular. The proposed work provides an extension towards VA in video sequences by incorporating the temporal dimension. The architecture is presented in detail and potential applications are investigated. We expect that the extended VA scheme can reveal interesting events across the sequence like occlusions and short occurrences of objects, providing a basis for video surveillance (e.g. intruder detection), segmentation, and summarization applications.
Keywords :
image sequences; surveillance; video signal processing; scene analysis; spatiotemporal visual attention architecture; video analysis; video sequence; video surveillance; Colored noise; Computer architecture; Computer science; Image analysis; Image segmentation; Image sequence analysis; Noise generators; Postal services; Spatiotemporal phenomena; Video surveillance;
Conference_Titel :
Multimedia Signal Processing, 2004 IEEE 6th Workshop on
Print_ISBN :
0-7803-8578-0
DOI :
10.1109/MMSP.2004.1436423
