DocumentCode :
2987548
Title :
Formula 1 onboard camera shot detector using motion activity areas
Author :
Raventós, Arnau ; Tarrés, Francese
Author_Institution :
EETAC, UPC-BARCELONA TECH, Barcelona, Spain
fYear :
2012
fDate :
27-29 June 2012
Firstpage :
1
Lastpage :
4
Abstract :
Shot detection in sports video sequences has been of great interest in the last years. In this paper, a new approach to detect onboard camera shots in compressed Formula 1 video sequences is presented. To that end, and after studying the characteristics of the shot, a technique based in the thresholding comparison between a high motion area and a stationary one has been devised. Efficient computation is achieved by direct decoding of the motion vectors in the MPEG stream. The shot detection process is done through a frame-by-frame hysteresis thresholding analysis. In order to enhance the results, a SVD shot boundary detector is applied. Promising results are presented that show the validity of the approach.
Keywords :
image motion analysis; image segmentation; image sequences; object detection; singular value decomposition; sport; vectors; video coding; Formula 1 onboard camera shot detector; MPEG stream; SVD shot boundary detector; motion activity areas; motion vectors; sports video sequences; thresholding comparison; Cameras; Detectors; Event detection; Shape; Transform coding; Vectors; Video sequences;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Content-Based Multimedia Indexing (CBMI), 2012 10th International Workshop on
Conference_Location :
Annecy
ISSN :
1949-3983
Print_ISBN :
978-1-4673-2368-0
Electronic_ISBN :
1949-3983
Type :
conf
DOI :
10.1109/CBMI.2012.6269800
Filename :
6269800
Link To Document :
بازگشت