Title :
Fast object tracking in digital video
Author :
Park, Dong Kwon ; Yoon, Ho Seok ; Won, Chee Sun
Author_Institution :
Dept. of Electron. Eng., Dongguk Univ., Seoul, South Korea
fDate :
8/1/2000 12:00:00 AM
Abstract :
This paper presents a fast semi-automatic semantic object-tracking algorithm for digital video. The proposed method consists of two steps, namely, intra-frame object extraction and the inter-frame object tracking. For the intra-frame segmentation, we try to minimize the human intervention by exploiting the automatic homogenous region segmentation. Then, to achieve a fast inter-frame object tracking, we propose to use 1-D projected motion estimation and an improved flooding method for the watershed algorithm
Keywords :
feature extraction; image segmentation; motion estimation; tracking; video signal processing; 1D projected motion estimation; automatic homogenous region segmentation; digital video; fast inter-frame object tracking; flooding method; inter-frame object tracking; intra-frame object extraction; intra-frame segmentation; semi-automatic semantic object-tracking algorithm; watershed algorithm; Floods; Humans; Image coding; Image segmentation; MPEG 4 Standard; Motion estimation; Object segmentation; Sun; Tracking; Video compression;
Journal_Title :
Consumer Electronics, IEEE Transactions on
