2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA) 2015
DOI: 10.1109/apsipa.2015.7415509
|View full text |Cite
|
Sign up to set email alerts
|

Detection of anomalous events in a tennis game using multimodal information

Abstract: Abstract-In the automatic analysis of a tennis game, it is important to detect some anomalous match events, such as "fault serve" and "ball out", as these events are crucial in understanding the progress of a game. Audio information can be used to detect these events, but it is unreliable, because of the acoustic mismatch between the training and the test data and interfering noise caused by spectator applause, players' yells etc. We present a framework to detect these events in which audio and visual informat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
4
0

Year Published

2019
2019
2019
2019

Publication Types

Select...
2
1

Relationship

2
1

Authors

Journals

citations
Cited by 3 publications
(4 citation statements)
references
References 14 publications
0
4
0
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%
“…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%
“…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%
“…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%