A GRIDDING HOUGH TRANSFORM FOR DETECTING THE STRAIGHT LINES IN SPORTS VIDEO (FriAmPO1)

Author(s) : Xinguo Yu (Institute for Infocomm Research, Singapore) Hoe Chee Lai (Nanyang Technological University, Singapore) Sophie Xiao Fan Liu (Oral Roberts University, United States of America) Hon Wai Leong (National University of Singapore, Singapore)

Abstract : A gridding Hough transform (GHT) is proposed to detect the straight lines in sports video, which is much faster and requires much less memory than the previous Hough transforms. The GHT uses the active gridding to replace the random point selection in the random Hough transforms because finding the linelets from the actively selected points is easier than from the randomly selected points. Existing straight-line Hough transforms require a lot of resources because they employ intensive computation to make sure that they will not fail for all kinds of straight lines. Considering the fact that the interested straight lines in sports video are long and sparse, this paper proposes the active gridding and linelets process two techniques. On account of these two techniques, the proposed GHT is a fast one using little memory. The experimental results show that the proposed GHT is faster than the random Hough transform (RHT) and the standard Hough transform (SHT) by 30% and 700% respectively and achieves a 97.5% recall, which is higher than both the SHT and the RHT.

Menu