The Proceedings of the International Conference on Sensing and Imaging, 2018 by Eric Todd Quinto & Nathan Ida & Ming Jiang & Alfred K. Louis

Author:Eric Todd Quinto & Nathan Ida & Ming Jiang & Alfred K. Louis
Language: eng
Format: epub
ISBN: 9783030308254
Publisher: Springer International Publishing

In order to improve the computational efficiency, the contour image of each player is equidimensional divided into h × w sub blocks without overlap in this paper [5]. Then, the normalized values of each sub block are calculated by using Eq. (4).

(4)

Among them, b(i) is the number of foreground pixels of the ith sub block and mv is the maximum of all b(i). In ℜ h × w space, the descriptor of the silhouette of a player in the tth frame is f t = [N 1, N 2, ⋯, N h × w]T and the outline of the player in the whole video can be correspondingly represented as vf = {f 1, f 2, ⋯, f T}. In fact, the original player contour representation v r can be considered as a special case based on block features, that is, the size of sub block is 1 × 1 (one pixel).

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.