A camera motion histogram descriptor for video shot classification

Muhammad Abul Hasan, Min Xu, Xiangjian He, Yi Wang

Research output: Journal PublicationArticlepeer-review

2 Citations (Scopus)

Abstract

In this paper, a novel camera motion descriptor is proposed for video shot classification. In the proposed method, raw motion information of consecutive video frames are extracted by computing the motion vector of each macroblock to form motion vector fields (MVFs). Next, a motion consistency analysis is applied on MVFs to eliminate the inconsistent motion vectors. Then, MVFs are divided into nine (3 × 3) local regions and the singular value decomposition (SVD) technique is applied on the motion vectors extracted from each local region in the temporal direction. Consistent motion vectors of a number of MVFs are compactly represented at a time to characterize temporal camera motion. Accordingly, each local region of the whole video shot is represented using a sequence of compactly represented vectors. Finally, the sequence of vectors is converted into a histogram to describe the camera motions of each local region. Combination of all the local histograms is considered as the camera motion descriptor of a video shot. The shot descriptors are used in a classifier to classify video shots. In this work, we use support vector machine (SVM) for performing classification tasks. The experimental results show that the proposed camera motion descriptor has strong discriminative capability to classify different camera motion patterns in professionally captured video shots effectively. We also show that our proposed approach outperforms two state-of-the-art video shot classification methods.

Original languageEnglish
Pages (from-to)11073-11098
Number of pages26
JournalMultimedia Tools and Applications
Volume74
Issue number24
DOIs
Publication statusPublished - 1 Dec 2015
Externally publishedYes

Keywords

  • Camera motion descriptor
  • Motion characterization
  • Shot classification
  • Singular value decomposition

ASJC Scopus subject areas

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'A camera motion histogram descriptor for video shot classification'. Together they form a unique fingerprint.

Cite this