Motion indexing of video

Sahouria, Emile; Zakhor, Avideh

doi:10.1109/icip.1997.638824

Cited by 43 publications

(27 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We address this by resampling trajectories to an appropriate length (as proposed in [19]): specifically, we linearly interpolate each coordinate sequence to a uniform length of 1024 (ie. 2 10 ) elements.…”

Section: Trajectory Representationsmentioning

confidence: 99%

“…Several recent trajectory classification approaches solve this problem by applying 1D signal approximation techniques to describe the X and Y coordinate sequences of a given trajectory with a fixed set of parameters. An early instance of this approach was proposed by Sahouria and Zakhor in [19], where Haar wavelet coefficients are used to represent trajectories for video indexing purposes. More recently, Naftel and Khalid have explored the use of the Discrete Fourier Transform and Chebyshev polynomial approximations for trajectory classification in [16], while Sillito and Fisher have adopted a least-squares cubic spline approximation as the basis for an incremental trajectory modelling algorithm in [20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Parametric Trajectory Representations for Behaviour Classification

Sillito¹,

Fisher²

2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

This paper presents an empirical comparison of strategies for representing motion trajectories with fixed-length vectors. We compare four techniques, which have all previously been adopted in the trajectory classification literature: least-squares cubic spline approximation, the Discrete Fourier Transform, Chebyshev polynomial approximation, and the Haar wavelet transform. We measure the class separability of five different trajectory datasets -ranging from vehicle trajectories to pen trajectories -when described in terms of these representations. Results obtained over a range of dimensionalities indicate that the different representations yield similar levels of class separability, with marginal improvements provided by Chebyshev and Spline representations. For the datasets considered here, each representation appears to yield better results when used in conjunction with a curve parametrisation strategy based on arc-length, rather than time. However, we illustrate a situation -pertinent to surveillance applications -where the converse is true.

show abstract

Section: Trajectory Representationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Parametric Trajectory Representations for Behaviour Classification

Sillito¹,

Fisher²

2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

show abstract

“…Motion information on the other hand could be extracted directly from uncompressed or compressed data [18,39,51,59,61,72] and used independently or in concert with other methods for retrieval.…”

Section: Object Motion and Event Analysismentioning

confidence: 99%

Multimedia Content Analysis and Indexing for Filtering and Retrieval Applications

Dimitrova¹

1999

InformingSciJ

View full text Add to dashboard Cite

“…As a result, the usefulness of such approaches is usually restricted to non-real-time applications. To counter these drawbacks, compressed domain methods have been proposed for spatiotemporal segmentation and indexing [3,4]. Although significantly faster than most pixeldomain algorithms, some of them cannot operate in real-time [5].…”

Section: Introductionmentioning

confidence: 99%

Object Segmentation and Ontologies for MPEG-2 Video Indexing and Retrieval

Mezaris

Strintzis

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.A novel approach to object-based video indexing and retrieval is presented, employing an object segmentation algorithm for the real-time, unsupervised segmentation of compressed image sequences and simple ontologies for retrieval. The segmentation algorithm uses motion information directly extracted from the MPEG-2 compressed stream to create meaningful foreground spatiotemporal objects, while background segmentation is additionally performed using color information. For the resulting objects, MPEG-7 compliant low-level indexing descriptors are extracted and are automatically mapped to appropriate intermediatelevel descriptors forming a simple vocabulary termed object ontology. This, combined with a relevance feedback mechanism, allows the qualitative definition of the high-level concepts the user queries for (semantic objects, each represented by a keyword) and the retrieval of relevant video segments. Experimental results demonstrate the effectiveness of the proposed approach.

show abstract

Motion indexing of video

Cited by 43 publications

References 11 publications

Parametric Trajectory Representations for Behaviour Classification

Parametric Trajectory Representations for Behaviour Classification

Multimedia Content Analysis and Indexing for Filtering and Retrieval Applications

Object Segmentation and Ontologies for MPEG-2 Video Indexing and Retrieval

Contact Info

Product

Resources

About