Statistical models of video structure for content analysis and characterization

Vasconcelos, Nuno; Lippman, Andrew

doi:10.1109/83.817595

Cited by 108 publications

(64 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vasconcelos et al propose in [83] a segmentation method using a Bayesian model of the editing process. For each frame a local activity measure is computed based on a tangent distance.…”

Section: Bayesian Approachesmentioning

confidence: 99%

A review of real-time segmentation of uncompressed video sequences for content-based search and retrieval

2003

View full text Add to dashboard Cite

We present in this paper a review of methods for segmentation of uncompressed video sequences. Video segmentation is usually performed in the temporal domain by shot change detection. In case of real-time segmentation, computational complexity is one of the criteria which has to be taken into account when comparing different methods. When dealing with uncompressed video sequences, this criterion is even more significant. However previous published reviews did not involve complexity criterion when comparing shot change detection methods. Only recognition rate and ability to classify detected shot changes were considered. So contrary to previous reviews we give here complexity of most of the described methods. We review in this paper an extensive set of methods presented in the literature and classify them in several parts, depending on the information used to detect shot changes. The earliest methods were comparing successive frames by relying on most simple elements, that is to say pixels. Comparison could be performed on a global level, so methods based on histograms were also proposed. Block-based methods have been considered to process data at an intermediate level, between local (using pixels) and global (using histograms) levels. More complex features can be involved, resulting in feature-based methods. Alternatively some methods rely on motion as a criterion to detect shot changes. Finally different kinds of information could be combined together in order to increase the quality of shot change detection. So our review will detail segmentation methods

show abstract

“…Vasconcelos et al propose in [83] a segmentation method using a Bayesian model of the editing process. For each frame a local activity measure is computed based on a tangent distance.…”

Section: Bayesian Approachesmentioning

confidence: 99%

A review of real-time segmentation of uncompressed video sequences for content-based search and retrieval

2003

View full text Add to dashboard Cite

show abstract

“…Specific to film classification, Vasconcelos et al proposed a feature-space based approach in [27]. In this work, two features of the previews, average shot length and shot activity, were used.…”

Section: Related Workmentioning

confidence: 99%

“…This feature was first proposed by Vasconcelos in [27]. The average shot length as a feature represents the tempo of a scene.…”

Section: A Shot Detection and Average Shot Lengthmentioning

confidence: 99%

On the use of computable features for film classification

Rasheed

Sheikh

Shah

2005

IEEE Trans. Circuits Syst. Video Technol.

157

104

View full text Add to dashboard Cite

Abstract-This paper presents a framework for the classification of feature films into genres, based only on computable visual cues. We view the work as a step toward high-level semantic film interpretation, currently using low-level video features and knowledge of ubiquitous cinematic practices. Our current domain of study is the movie preview, commercial advertisements primarily created to attract audiences. A preview often emphasizes the theme of a film and hence provides suitable information for classification. In our approach, we classify movies into four broad categories: Comedies, Action, Dramas, or Horror films. Inspired by cinematic principles, four computable video features (average shot length, color variance, motion content and lighting key) are combined in a framework to provide a mapping to these four highlevel semantic classes. Mean shift classification is used to discover the structure between the computed features and each film genre. We have conducted extensive experiments on over a hundred film previews and notably demonstrate that low-level visual features (without the use of audio or text cues) may be utilized for movie classification. Our approach can also be broadened for many potential applications including scene understanding, the building and updating of video databases with minimal human intervention, browsing, and retrieval of videos on the Internet (video-on-demand) and video libraries.

show abstract

“…This remains an open problem at the source of active research activities. In [9], statistical models for components of the video structure are introduced to classify video sequences into different genres. The analysis of image motion is widely exploited for the segmentation of videos into meaningful units or for event recognition.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Extraction of Semantic Dynamic Content from Videos with Probabilistic Motion Models

Piriou

Bouthémy

Yao

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The exploitation of video data requires to extract information at a rather semantic level, and then, methods able to infer "concepts" from low-level video features. We adopt a statistical approach and we focus on motion information. Because of the diversity of dynamic video content (even for a given type of events), we have to design appropriate motion models and learn them from videos. We have defined original and parsimonious probabilistic motion models, both for the dominant image motion (camera motion) and the residual image motion (scene motion). These models are learnt off-line. Motion measurements include affine motion models to capture the camera motion, and local motion features for scene motion. The two-step event detection scheme consists in pre-selecting the video segments of potential interest, and then in recognizing the specified events among the pre-selected segments, the recognition being stated as a classification problem. We report accurate results on several sports videos.

show abstract

Statistical models of video structure for content analysis and characterization

Cited by 108 publications

References 48 publications

A review of real-time segmentation of uncompressed video sequences for content-based search and retrieval

A review of real-time segmentation of uncompressed video sequences for content-based search and retrieval

On the use of computable features for film classification

Extraction of Semantic Dynamic Content from Videos with Probabilistic Motion Models

Contact Info

Product

Resources

About