Scene content classification from MPEG coded bit streams

Dawood, Ali; Ghanbari, Mohammed

doi:10.1109/mmsp.1999.793841

Cited by 9 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While motion patterns often convey some semantic information, especially in sports video, they have been used often only as a low-level attribute in most of the existing video analysis systems. By extracting texture and motion features, the scene contents of video are classified into 9 categories in [9]. The categories are defined according to 3 levels of texture complexity and 3 levels of motion intensity each, namely, low, medium, and high.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Motion Pattern-Based Video Classification and Retrieval

Zhang

2003

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Today′s content-based video retrieval technologies are still far from human′s requirements. A fundamental reason is the lack of content representation that is able to bridge the gap between visual features and semantic conception in video. In this paper, we propose a motion pattern descriptor, motion texture that characterizes motion in a generic way. With this representation, we design a semantic classification scheme to effectively map video clips to semantic categories. Support vector machines (SVMs) are used as the classifiers. In addition, this scheme also improves significantly the performance of motion-based shot retrieval due to the comprehensiveness and effectiveness of motion pattern descriptor and the semantic classification capability as shown by experimental evaluations.

show abstract

Section: Related Workmentioning

confidence: 99%

“…where (p, q) = {(0, 0), (1, 0), (0, 1), (2, 0), (0, 2), (3, 0), (0, 3), (4, 0), (0, 4)}. Based on these moments, we compute 9 values with specific physical meaning (4), (5), (6), (7), (8), (9), and (10). These values can be normalized values by the size of slices if it is necessary.…”

Section: Moments Measuringmentioning

confidence: 99%