A highlight scene detection and video summarization system using 'audio' feature for a personal video recorder

Otsuka, I.; Nakane, K.; Divakaran, Ajay; Hatanaka, Keiji; Ogawa, Michio

doi:10.1109/icce.2005.1429798

Cited by 12 publications

(8 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All extracted R-images of a story unit were resized and organized into a single regular-sized image following a predefined visual layout called the poster. In [20], Otsuka et al proposed an automatic sports highlights detection system using only audio features and Gaussian mixture models. Also, in [21], the authors proposed a probabilistic framework to detect sport events using webcast texts.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Keyframe-based Video Summarization Using QR-Decomposition and Modified -Means Clustering

Amiri

2010

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

We propose a novel hierarchical keyframe-based video summarization system using QR-decomposition. Specially, we attend to the challenges of defining some measures to detect the dynamicity of a shot and video and extracting appropriate keyframes that assure the purity of video summary. We derive some efficient measures to compute the dynamicity of video shots using QRdecomposition, and we utilize it in detecting the number of keyframes that must be selected from each shot. Also, we derive a theorem that illustrates an important property of QR-decomposition. We utilize it in order to summarize video shots with low redundancy. The proposed algorithm is implemented and evaluated on TRECVID 2006 benchmark platform. Compared with other algorithms, our results are among the best.

show abstract

Section: Related Workmentioning

confidence: 99%

Hierarchical Keyframe-based Video Summarization Using QR-Decomposition and Modified -Means Clustering

Amiri

2010

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…However, it is challenging to realize them for the currently used eagle eye playback and video assistance system, which can only detect the trajectory of the balls by the high-cost hardware system and complex data processing methods [7]. Moreover, these monitoring systems rely on time delay to calculate the data, which makes the detection difficult to be real-time and high-frequently available [8]. A more effective monitoring system is desirable for the contact between rackets and balls.…”

Section: Introductionmentioning

confidence: 99%

A self-power flexible piezoelectric sensing system for badminton training monitoring

Wang

Fan

Feng

2021

IEICE Electron. Express

View full text Add to dashboard Cite

Monitoring of training, especially the use of soft devices, is difficult but has become more and more important for human health. In this paper, a self-power flexible piezoelectric sensing system for badminton training based on polyvinylidene fluoride (PVDF) piezoelectric film sensor is designed and experimentally verified. The sensing array is divided as 3 ◊ 3 chessboard-like areas, which contain thin-film transductors to determine the hitting position and force. The system owns a linear relationship between force and generated electric signal with a sensitivity of 0.377 V/N and the minimum sampling interval of 1s. Furthermore, the piezoelectric Lead Zirconium titanite (PZT) patch behind the racket is employed as a power source to support the sensing circle. This work paves a new way for the application of artificial intelligence in the human health area and the Internet of Things.

show abstract

“…Much research has been done on the topic of automatic detection of highlights in soccer and other sports. However, only a few of these approaches (for example, the system described in [1]) have actually been implemented in consumer applications for entertainment purposes. The challenge in this topic is that it is difficult to make sure that users are given all highlights that they expect, even if the performance of the automatic highlight detector is close to 100%.…”

Section: Introductionmentioning

confidence: 99%

User Test of Soccer Highlights Application

Wang

Fonseca

Zoetekouw

2008

Electronic Workshops in Computing

View full text Add to dashboard Cite

This paper describes an evaluation of a consumer application for soccer highlights detection, which combines advanced user interaction with an underlying automatic highlights detection algorithm. The application was developed for a home entertainment setting, i.e., for non-professional use, and was implemented on a Media Center PC with a remote control. The evaluation uses a qualitative assessment to measure the participants' satisfaction with the application, and investigates their satisfaction regarding several important factors, such as the participants' expectations and their satisfaction with the highlights. In the evaluation, we found that the participants' expectations regarding a soccer highlights detection application vary widely, and there is a gap between what participants expect and what any automatic detection application can provide. Despite this gap, the results from the qualitative assessment indicate that the application is very positively perceived by the participants. The results indicate that the participants showed positive satisfaction with the application, especially in its ease-of-learning, ease-of-use, and the feeling of being in control. Moreover, the results suggest new and further tuned user requirements that help improve satisfaction with the application.

show abstract

A highlight scene detection and video summarization system using 'audio' feature for a personal video recorder

Cited by 12 publications

References 1 publication

Hierarchical Keyframe-based Video Summarization Using QR-Decomposition and Modified -Means Clustering

Hierarchical Keyframe-based Video Summarization Using QR-Decomposition and Modified -Means Clustering

A self-power flexible piezoelectric sensing system for badminton training monitoring

User Test of Soccer Highlights Application

Contact Info

Product

Resources

About