Structure analysis of soccer video with domain knowledge and hidden Markov models

Xie, Lexing; Xu, Peng; Chang, Shih-Fu; Divakaran, Ajay; Sun, Huifang

doi:10.1016/j.patrec.2004.01.005

Cited by 199 publications

(155 citation statements)

References 7 publications

Supporting

Mentioning

142

Contrasting

Unclassified

Order By: Relevance

“…In Table 1, the performance of the proposed method is compared with the motion representation approaches for providing motion information to HMM-based systems presented in [6] and [7]. Specifically, Gibert et al estimates the principal motion direction of every frame [6], while Xie et al calculates the motion intensity at frame level [7].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Estimation and representation of accumulated motion characteristics for semantic event detection

Papadopoulos

Mezaris

Kompatsiaris

et al. 2008

2008 15th IEEE International Conference on Image Processing

View full text Add to dashboard Cite

In this paper, a motion-based approach for detecting high-level semantic events in video sequences is presented. Its main characteristic is its generic nature, i.e. it can be directly applied to any possible domain of concern without the need for domain-specific algorithmic modifications or adaptations. For realizing event detection, the examined video sequence is initially segmented into shots and for every resulting shot appropriate motion features are extracted. Then, Hidden Markov Models (HMMs) are employed for performing the association of each shot with one of the high-level semantic events that are of interest in any given domain. Regarding the motion feature extraction procedure, a new representation for providing local-level motion information to HMMs is presented, while motion characteristics from previous frames are also exploited. Experimental results as well as comparative evaluation from the application of the proposed approach in the domain of news broadcast video are presented.

show abstract

Section: Resultsmentioning

confidence: 99%

“…, τ = 0, 1, ... , (7) where t is the current frame, τ denotes previously selected frames and w(τ ) is a time-dependent normalization factor. The latter is modeled by the following time descending function:…”

Section: Accumulated Motion Energy Field Computationmentioning

confidence: 99%

Estimation and representation of accumulated motion characteristics for semantic event detection

Papadopoulos

Mezaris

Kompatsiaris

et al. 2008

2008 15th IEEE International Conference on Image Processing

View full text Add to dashboard Cite

show abstract

“…Based on whether prior knowledge of the program structure is adopted or not, previous work in the abundant literature on TV program structuring can be classified in two categories: prior-knowledge-based methods and prior-knowledge-free methods Numerous studies use prior knowledge of the program structure to segment programs or to build models. For instance, [27,16] use extensive prior knowledge of sports and editing rules to model the structure of sport videos. [27] targets soccer videos and relies on low-level features to detect particular actions or states in soccer games.…”

Section: Related Workmentioning

confidence: 99%

“…For instance, [27,16] use extensive prior knowledge of sports and editing rules to model the structure of sport videos. [27] targets soccer videos and relies on low-level features to detect particular actions or states in soccer games. Hidden Markov models are used in [16] for tennis video structuring, relying on prior information about tennis video content and production rules.…”

Section: Related Workmentioning

confidence: 99%

“…The most traditional way to realize automatic TV program segmentation is either classification strategies [10,27] or event detection approaches [4,17], which are mostly supervised approaches. Unsupervised approaches for program segmentation were also addressed recently, where audiovisual consistency [5] and clustering-based methods [15] are considered.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Content-based unsupervised segmentation of recurrent TV programs using grammatical inference

Vallet

Carrive

et al. 2017

Multimed Tools Appl

View full text Add to dashboard Cite

TV program segmentation raised as a major topic in the last decade for the task of high quality indexing of multimedia content. Earlier studies of TV program segmentation are either highly supervised (e.g., event detection) or too specific to a certain type of program (e.g., cluster-based methods), which is not practically usable for indexing tasks because of the lack of generality of programs types. In this paper, we address the problem of unsupervised TV program segmentation by leveraging grammatical inference, i.e., discovering a common structural model shared by a collection of episodes of a recurrent TV program by finding an optimal alignment of structural elements across episodes. Structural elements referring to a video segment with a particular syntactic meaning with respect to the video structure. The use of symbolic representation of structural elements makes grammatical inference feasible to be applied on TV program modeling, and makes TV program segmentation possible to rely on only minimal domain knowledge. The proposed approach is operated in two phases. The first phase aims at obtaining a symbolic representation of each episode, where the elements relevant to the structure are discovered based on recurrence mining. The second phase is that of grammatical inference from the symbolic representation of episodes. We investigate two inference techniques, one based on multiple sequence alignment and one relying on uniform resampling, to infer structural grammars for TV programs. A model of the structure is derived from the structural grammars and used to predict the structure of new episodes. Comparative evaluation on two gramBingqing Qu

show abstract

Soccer/World Football

Brillinger

2011

Wiley Encyclopedia of Operations Research and Management Science

View full text Add to dashboard Cite

This article constitutes a review of magagement science, operations research, and statistics as they arise in the study of data arising from the world of soccer/football. The data may have been collected during a game, may be summaries after games, or after a season, or after a tournament, or over many years. The main sections of the article include Data Collection and Descriptive Analyses, Stochastic Modeling (with subsections Between Game Modeling and Within Game Modeling), Ranking, Tournaments and Scheduling, Game Theory, and Economics and Management. The reference list contains 167 books and articles. The analytic study of the field has reached maturity following the contributions of many individuals and institutions.

show abstract

Structure analysis of soccer video with domain knowledge and hidden Markov models

Cited by 199 publications

References 7 publications

Estimation and representation of accumulated motion characteristics for semantic event detection

Estimation and representation of accumulated motion characteristics for semantic event detection

Content-based unsupervised segmentation of recurrent TV programs using grammatical inference

Soccer/World Football

Contact Info

Product

Resources

About