Real-Time Compressed-Domain Spatiotemporal Segmentation and Ontologies for Video Indexing and Retrieval

Mezaris, Vasileios; Kompatsiaris, Ioannis; Boulgouris, Nikolaos V.; Strintzis, M.G.

doi:10.1109/tcsvt.2004.826768

Cited by 137 publications

(82 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…2 that have a strong temporal dimension (i.e. features 5,6,7,9,11,13), the use of the proposed combination of SIFT-and LIFT-based BoW leads to an increase of MAP by 63.8% over using the SIFT-based BoW alone. …”

Section: Resultsmentioning

confidence: 99%

“…Long-term region trajectories in particular, rather than the motion at the frame level, was shown in many works to be very useful in video segmentation, indexing and retrieval (e.g. [7]). Similarly to other analysis tasks, the use of video data in excess of one single key-frame (e.g.…”

Section: Related Workmentioning

confidence: 99%

“…of frames; subsequently, the 8 parameters of the bilinear motion model, representing the camera motion, are estimated from this field using least-squares estimation and an iterative rejection scheme, as in [7]. Then ψ x,t k and ψ y,t k are eventually calculated as the differences between the initial displacement of the corresponding interest point's centroid between times t − 1 and t, and the estimated camera motion at the location of the centroid.…”

Section: Feature Track Extractionmentioning

confidence: 99%

See 2 more Smart Citations

Local Invariant Feature Tracks for High-Level Video Feature Extraction

Mezaris

Dimou

Kompatsiaris

2012

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

This paper builds upon previous work on local interest point detection and description to propose the extraction and representation of novel Local Invariant Feature Tracks (LIFT). These features compactly capture not only the spatial attributes of 2D local regions, as in SIFT and related techniques, but also their long-term trajectories in time. This and other desirable properties of LIFT allow the generation of Bags-of-Spatiotemporal-Words models that facilitate capturing the dynamics of video content, which is necessary for detecting high-level video features that by definition have a strong temporal dimension. Preliminary experimental evaluation and comparison of the proposed approach reveals promising results.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Feature Track Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Local Invariant Feature Tracks for High-Level Video Feature Extraction

Mezaris

Dimou

Kompatsiaris

2012

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…Instead, information embedded in the encoded bit-stream, such as motion vectors (MVs), transform coefficients and block prediction modes -information often referred to as compressed domain features -can be used as auxiliary information. For example, Babu et al [3], Mezariz et al [4] and Porikli et al [5] present different methods of using MVs and transform coefficients in video segmentation. Variations of block prediction modes are used to filter motion information by Bruyne et al [6], to identify regions-of-interest in image sequences.…”

Section: Introductionmentioning

confidence: 99%

Application-aware video coding architecture using camera and object motion-models

Rajakaruna

Fernando

Calic

2011

2011 6th International Conference on Industrial and Information Systems

View full text Add to dashboard Cite

Abstract-The proliferation of video consumption, especially over mobile devices, has created a demand for efficient interactive video applications and high-level video analysis. This is particularly significant in real-time applications and resourcelimited scenarios. Pixel-domain video processing is often inefficient for many of these applications due to its complexity, whereas compressed domain processing offer fast but unreliable results. In order to achieve fast and effective video processing, this paper proposes a novel video encoding architecture that facilitate efficient compressed domain processing, while maintaining compliance with the mainstream coding standards. This is achieved by optimizing the accuracy of motion information embedded in the compressed video, in addition to compression efficiency. In a motion detection application, we demonstrate that the motion estimated by the proposed encoder can be directly used to extract object information, as opposed to conventionally coded video. The incurred rate distortion overheads can be weighed against the reduced processing required for video analysis targeting a wide spectrum of computer vision applications.

show abstract

“…Architecture of the integrated system labels assigned to multimedia objects. Indicative approaches for constructing multimedia ontologies are the ones presented in [7], [11] [13]. The major open issues here concern the automatic mapping between low level audio-visual features and high level domain concepts, the automated population from unconstrained content and when there are no metadata attached to the content.…”

Section: Multimedia Ontologiesmentioning

confidence: 99%

Knowledge Acquisition from Multimedia Content using an Evolution Framework

Kosmopoulos

Petridis

Pratikakis

et al.

IFIP International Federation for Information Processing

View full text Add to dashboard Cite

Abstract. We propose an approach to knowledge acquisition, which uses multimedia ontologies for fused extraction of semantics from multiple modalities, and feeds back the extracted information, aiming to evolve knowledge representation. This paper presents the basic components of the proposed approach and discusses the open research issues focusing on the fused information extraction that will enable the development of scalable and precise knowledge acquisition technology.

show abstract

Real-Time Compressed-Domain Spatiotemporal Segmentation and Ontologies for Video Indexing and Retrieval

Cited by 137 publications

References 45 publications

Local Invariant Feature Tracks for High-Level Video Feature Extraction

Local Invariant Feature Tracks for High-Level Video Feature Extraction

Application-aware video coding architecture using camera and object motion-models

Knowledge Acquisition from Multimedia Content using an Evolution Framework

Contact Info

Product

Resources

About