Detection of anomalous events in a tennis game using multimodal information

Huang, Qiang; Cox, Stephen J.

doi:10.1109/apsipa.2015.7415509

Cited by 3 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to extract audio features for event classification, seven types of audio events are defined [17], as summarised in Table 1. Note that the set of audio events do not completely overlap with the four events for annotation (serve, bounce, hit, net), as some of the events for annotation e.g.…”

Section: Audio Processingmentioning

confidence: 99%

Automatic annotation of tennis games: An integration of audio, vision, and learning

Yan

Kittler

Windridge

et al. 2014

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

Fully automatic annotation of tennis game using broadcast video is a task with a great potential but enormous challenges. In this paper we describe our approach to this task, which integrates computer vision, machine listening, and machine learning. At the low level processing, we improve upon our previously proposed state-of-the-art tennis ball tracking algorithm and employ audio signal processing techniques to detect key events and construct features for classifying the events. At the high level analysis, we model event classification as a sequence labelling problem, and investigate four machine learning techniques using simulated event sequences. Finally, we evaluate our proposed approach on three real world tennis games, and discuss the interplay between audio, vision and learning. To the best of our knowledge, our system is the only one that can annotate tennis game at such a detailed level.

show abstract

Section: Audio Processingmentioning

confidence: 99%

Automatic annotation of tennis games: An integration of audio, vision, and learning

Yan

Kittler

Windridge

et al. 2014

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Presence of ball-like objects in the background also leads to false positives in such approaches. Offline ball tracking approaches like Data Association (DA) was used for tracking only tennis ball in sim- pler conditions [21][22][23]. Similar to DA, graph based approach can handle occlusion for a very small duration.…”

Section: Introductionmentioning

confidence: 99%

A deep learning ball tracking system in soccer videos

Kamble¹,

Keskar²,

Bhurchandi³

2019

Opto-Electronics Review

View full text Add to dashboard Cite

Increasing interest, enthusiasm of sport lovers, and economics involved offer high importance to sports video recording and analysis. Being crucial for decision making, ball detection and tracking in soccer has become a challenging research area. This paper presents a novel deep learning approach for 2D ball detection and tracking (DLBT) in soccer videos posing various challenges. A new 2-stage buffer median filtering background modelling is used for moving objects blob detection. A deep learning approach for classification of an image patch into three classes, i.e. ball, player, and background is initially proposed. Probabilistic bounding box overlapping technique is proposed further for robust ball track validation. Novel full and boundary grid concepts resume tracking in ball track lost and ball out of frame situations. DLBT does not require human intervention to identify ball from the initial frames unlike the most published algorithms. DLBT yields extraordinary accurate and robust tracking results compared to the other contemporary 2D trackers even in presence of various challenges including very small ball size and fast movements.

show abstract

“…the lack of motion smoothness constraints). More recently, Huang et al [9] described a Viterbi-based method to estimate ball trajectory: however, it loses some precision in tracking the target, mainly because of the lack of a well-defined motion model.…”

Section: Introductionmentioning

confidence: 99%

“…4(b) shows the final estimated trajectory. Table.1 summarizes the performance of our two-layered (TL) approach compared with a baseline, which is the results using the method introduced in our previous work [9]. The baseline method uses the Viterbi algorithm to search a globally smooth trajectory amongst weighted candidates, but there is no motion model and the Viterbi search is less sophisticated.…”

mentioning

confidence: 99%

A two layered data association approach for ball tracking

Zhou

Huang

Xie

et al. 2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

Ball-tracking is a key technology in processing and analyzing a ball game. Because of the complexity of visual scenes, a large number of objects are usually selected as candidates for the ball, leading to incorrect identification, and conversely, the true position of the ball may sometimes be missed. In this paper, we propose a two layered data association method to improve the robustness of ball-tracking. At a local layer, we use a sliding window based Token Transfer method to generate a set of sub-trajectory candidates. At a global layer, a single ball trajectory is obtained by applying a dynamic programming based splice method to a graph consisting of the sub-trajectory candidates. We evaluated our approach on tennis matches from the Australian Open and the U.S. Open, and the results obtained show that our approach outperforms the state-of-art approach by around 30 %.

show abstract

Detection of anomalous events in a tennis game using multimodal information

Cited by 3 publications

References 14 publications

Automatic annotation of tennis games: An integration of audio, vision, and learning

Automatic annotation of tennis games: An integration of audio, vision, and learning

A deep learning ball tracking system in soccer videos

A two layered data association approach for ball tracking

Contact Info

Product

Resources

About