A review of vision-based systems for soccer video analysis

D’Orazio, Tiziana; Leo, Marco

doi:10.1016/j.patcog.2010.03.009

Cited by 123 publications

(35 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid too frequent camera switching, this method [8] modeled the prior selection state using Dynamic Bayesian Networks. D'Orazio and Leo [11] presented a detailed review of vision-based systems for soccer game video analysis, in which they detailed that the type of features extracted for vision-based sports game analysis vary based on the application under study and may include dominant color, color histogram, camera motion, corner points, ball and player detection, field characteristics detection, texture, and player recognition [11]. Multi-camera sports videos are recorded using professional cameras capable of performing stable pan, tilt and zoom motions [11].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

ViComp: composition of user-generated videos

Bano

Cavallaro

2015

Multimed Tools Appl

View full text Add to dashboard Cite

We propose ViComp, an automatic audio-visual camera selection framework for composing uninterrupted recordings from multiple user-generated videos (UGVs) of the same event. We design an automatic audio-based cut-point selection method to segment the UGV. ViComp combines segments of UGVs using a rank-based camera selection strategy by considering audio-visual quality and camera selection history. We analyze the audio to maintain audio continuity. To filter video segments which contain visual degradations, we perform spatial and spatio-temporal quality assessment. We validate the proposed framework with subjective tests and compare it with state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

“…This includes camera selection for lecture webcast [9,41] and meetings [27,42], sports video broadcast [8,11,38], home-video summarization [7,15], and multi-camera mashup generation [30,35]. In video editing for summarization, the continuity of the event is disregarded and only key frames are included in the output video.…”

Section: Related Workmentioning

confidence: 99%

ViComp: composition of user-generated videos

Bano

Cavallaro

2015

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…We obtained the position of the ball through manual labeling and a basic interpolation procedure since our main focus is the viewpoint navigation but not automatic ball tracking. Some vision-based and sensor-based tracking techniques are being researched separately for this purpose [31].…”

Section: Multi-view Video Datasetmentioning

confidence: 99%

Personal Viewpoint Navigation Based on Object Trajectory Distribution for Multi-View Videos

Wang

Hara

Enokibori

et al. 2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYMulti-camera videos with abundant information and high flexibility are useful in a wide range of applications, such as surveillance systems, web lectures, news broadcasting, concerts and sports viewing. Viewers can enjoy an enhanced viewing experience by choosing their own viewpoint through viewing interfaces. However, some viewers may feel annoyed by the need for continual manual viewpoint selection, especially when the number of selectable viewpoints is relatively large. In order to solve this issue, we propose an automatic viewpoint navigation method designed especially for sports. This method focuses on a viewer's personal preference for viewpoint selection, instead of common and professional editing rules. We assume that different trajectory distributions of viewing objects cause a difference in the viewpoint selection according to personal preference. We learn the relationship between the viewer's personal viewpoint-selection tendency and the spatio-temporal game context represented by the objects trajectories. We compare three methods based on Gaussian mixture model, SVM with a general histogram and SVM with a bag-of-words to seek the best learning scheme for this relationship. The performance of the proposed methods are evaluated by assessing the degree of similarity between the selected viewpoints and the viewers' edited records. key words: multi-view video navigation, user preference, Gaussian mixture model

show abstract

“…Preliminary results suggest that to overcome occlusions, the classifier detects players and resample the centre of gravity [14]. Despite their promising results, some questions about the applicability of this technique still remain due to its computational complexity [15]. Moreover, this tracking strategy only allows to identify the players without any memory properties.…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, it is those memory properties that may provide further information about the variability, predictability and stability level of each player. Moreover, these systems are based uniquely on colour segmentation eve despite soccer matches can occur at different moments of the day with or without artificial light [15]. It is due to those reasons that many scientific studies have been using the manual tracking as a low-cost solution to overcome the expensive automatic multi-player tracking.…”

Section: Introductionmentioning

confidence: 99%

Analysis of football player’s motion in view of fractional calculus

2013

View full text Add to dashboard Cite

Abstract:Accurately retrieving the position of football players over time may lay the foundations for a whole series of possible new performance metrics for coaches and assistants. Despite the recent developments of automatic tracking systems, the misclassification problem (i.e., misleading a given player by another) still exists and requires human operators as final evaluators. This paper proposes an adaptive fractional calculus (FC) approach to improve the accuracy of tracking methods by estimating the position of players based on their trajectory so far. One half-time of an official football match was used to evaluate the accuracy of the proposed approach under different sampling periods of 250, 500 and 1000 ms. Moreover, the performance of the FC approach was compared with position-based and velocity-based methods. The experimental evaluation shows that the FC method presents a high classification accuracy for small sampling periods. Such results suggest that fractional dynamics may fit the trajectory of football players, thus being useful to increase the autonomy of tracking systems. PACS

show abstract

A review of vision-based systems for soccer video analysis

Cited by 123 publications

References 68 publications

ViComp: composition of user-generated videos

ViComp: composition of user-generated videos

Personal Viewpoint Navigation Based on Object Trajectory Distribution for Multi-View Videos

Analysis of football player’s motion in view of fractional calculus

Contact Info

Product

Resources

About