A Tennis Video Indexing Approach Through Pattern Discovery in Interactive Process

Wang, Peng; Cai, Rui

doi:10.1007/978-3-540-30541-5_7

Cited by 14 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, patterns associated with offenses and defenses in tennis are discovered in an unsupervised manner [6]. Generally, most current approaches to video pattern discovery use two steps: i) decompose a video stream into a discrete symbol sequence, either by clustering [6] or probabilistic models [1]; and ii) enumerate repetitive patterns in the symbol sequence using techniques similar to that for DNA sequence analysis in bioinformatics [2].…”

Section: Introductionmentioning

confidence: 99%

A probabilistic template-based approach to discovering repetitive patterns in broadcast videos

Wang

Liu

2005

Proceedings of the 13th Annual ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

There are usually repetitive sub-segments in broadcast videos, which may be associated with high-level concepts or events, e.g., news footage, repeated scores in basketball. Unsupervised mining techniques provide generic solutions to discovering such temporal patterns in various video genres, which are currently the subject of great interests to researchers working on multimedia content analysis. In this paper, we propose a novel approach to automatically detecting repetitive patterns in a video stream. In this approach, a video stream is first transformed to a symbol sequence via the spectral clustering algorithm. After computing the transition probabilities of any two symbols in temporal evolution, we produce a set of probabilistic templates to characterize the patterns of potential interest. Finally, we verify each probabilistic template by measuring the similarities between the video subsegments and the template. Evaluations on various sports videos show promising results.

show abstract

Section: Introductionmentioning

confidence: 99%

A probabilistic template-based approach to discovering repetitive patterns in broadcast videos

Wang

Liu

2005

Proceedings of the 13th Annual ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…The key techniques used in these approaches are tracking the trajectories of the players and the ball with the assistance of domain knowledge [13]- [16] and recognizing the actions of the players [9]. Sudhir et al [13] exploited the domain knowledge of tennis video to develop a court line detection algorithm and a player tracking algorithm to identify tactics-related events.…”

Section: B Tactic Strategy Analysis For Sports Gamesmentioning

confidence: 99%

“…In [15], the tennis games were attempted to be classified into 58 winning patterns for training purpose based on tracking the ball movement from broadcast video. Wang et al [16] presented a novel approach for tennis video indexing by mining the salient tactic patterns in the match process. Unlike trajectory-based algorithm, a novel action-driven tactic analysis approach was proposed in [9] for the tennis game, which is able to discover the insight of the stroke performance of the players.…”

Section: B Tactic Strategy Analysis For Sports Gamesmentioning

confidence: 99%

“…The final route pattern RP of the attack event is determined by (16) Because there are two pattern categories, the equal sign is assigned for the side attack so as to avoid the occurrence of marginal classification. This is reasonable due to our observation that there are more side attacks than center attacks in the soccer game.…”

Section: A Route Pattern Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Event Tactic Analysis Based on Broadcast Sports Video

Zhu

Huang³

et al. 2009

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-Most existing approaches on sports video analysis have concentrated on semantic event detection. Sports professionals, however, are more interested in tactic analysis to help improve their performance. In this paper, we propose a novel approach to extract tactic information from the attack events in broadcast soccer video and present the events in a tactic mode to the coaches and sports professionals. We extract the attack events with far-view shots using the analysis and alignment of web-casting text and broadcast video. For a detected event, two tactic representations, aggregate trajectory and play region sequence, are constructed based on multi-object trajectories and field locations in the event shots. Based on the multi-object trajectories tracked in the shot, a weighted graph is constructed via the analysis of temporal-spatial interaction among the players and the ball. Using the Viterbi algorithm, the aggregate trajectory is computed based on the weighted graph. The play region sequence is obtained using the identification of the active field locations in the event based on line detection and competition network. The interactive relationship of aggregate trajectory with the information of play region and the hypothesis testing for trajectory temporal-spatial distribution are employed to discover the tactic patterns in a hierarchical coarse-to-fine framework. Extensive experiments on FIFA World Cup 2006 show that the proposed approach is highly effective.

show abstract

“…The main difficulty lies in the semantic-level representation of what viewer recognizes as "interesting" events. Since the broadcast styles of different sports genres vary drastically, researchers have targeted the individual games such as soccer (football) [6], [7], [12]- [16], tennis [17], [18], cricket [19], [20], basketball [21], [22], baseball [23]- [26], volleyball [27], golf [28].…”

Section: Introductionmentioning

confidence: 99%

Bayesian Network-Based Customized Highlight Generation for Broadcast Soccer Videos

Kolekar

Sengupta

2015

IEEE Trans. on Broadcast.

View full text Add to dashboard Cite

Sports highlight generation techniques aim at condensing a full-length video to a significantly shortened version that still preserves the main interesting content of the original video. In this paper, we present the system for automatically generating the highlights from sports TV broadcasts. The proposed system detects exciting clips based on audio features and then classify the individual scenes within the clip into events such as replay, player, referee, spectator, and players gathering. A probabilistic Bayesian belief network based on observed events is used to assign semantic concept-labels to the exciting clips, such as goals, saves, yellow-cards, red-cards, and kicks in soccer video sequences. The labeled clips are selected according to their degree of importance to include in the highlights. We have successfully generated highlights from soccer video sequences.Index Terms-Bayesian belief network (BBN), sports highlights, semantic annotation, event detection, soccer video indexing.

show abstract

A Tennis Video Indexing Approach Through Pattern Discovery in Interactive Process

Cited by 14 publications

References 2 publications

A probabilistic template-based approach to discovering repetitive patterns in broadcast videos

A probabilistic template-based approach to discovering repetitive patterns in broadcast videos

Event Tactic Analysis Based on Broadcast Sports Video

Bayesian Network-Based Customized Highlight Generation for Broadcast Soccer Videos

Contact Info

Product

Resources

About