Football Video Research Articles

Spotting Football Events Using Two-Stream Convolutional Neural Network and Dilated Recurrent Neural Network

This paper addresses the problem of event detection and localization in long football (soccer) videos. Our key idea is that understanding the long-range dependencies between video frames is imperative for accurate event localization in long football videos. Additionally, proper event detection is not likely for fast movements in football videos without considering mid-range and short-range correlations between neighboring video frames. We argue that event spotting can be considerably improved by considering short-range to long-range frame dependencies in a unified architecture. To model long-range and mid-range dependencies, we propose to use the dilated recurrent neural network (DilatedRNN) with long short-term memory (LSTM) units, grounded on two-stream convolutional neural network (Two-stream CNN) features. While two-stream CNN extracts local spatiotemporal features necessary for fine-level details, the DilatedRNN makes the information obtained from distant frames available for the classifier and spotting algorithms. Evaluating our event spotting algorithm on the largest publicly available benchmark football dataset –SoccerNet– shows an accuracy improvement of 0.8% - 13.6% compared to state of the art, and up to 30.1% accuracy gain in comparison to the baselines. We also investigate the contribution of each neural network component in spotting accuracy through an extensive ablation study.

Event detection in sports video based on audio-visual and support vector machine. Case-study: football

In this paper, we propose a novel audio-visual feature-based framework for event detection in field sports broadcast video. The system is evaluated via a case-study involving MPEG encoded football video. Specifically, the features gathered by various feature detectors is combined by means of a support vector machine which infers the occurrence of an event based on a model generated during a training phase, utilising a corpus of 2.5 hours of content. The system is evaluated using 2.5 hours of separate test match content.

Event detection in sports video based on audio-visual and support vector machine. Case-study: football

In this paper, we propose a novel audio-visual feature-based framework for event detection in field sports broadcast video. The system is evaluated via a case-study involving MPEG encoded football video. Specifically, the features gathered by various feature detectors is combined by means of a support vector machine which infers the occurrence of an event based on a model generated during a training phase, utilising a corpus of 2.5 hours of content. The system is evaluated using 2.5 hours of separate test match content.

Changes in Cognitive Functions Following Violent and Football Video Games in Young Male Volunteers by Studying Brain Waves.

Introduction:This research investigated the effects of violent and football video games on cognitive functions, cortisol levels, and brain waves.Methods:A total of 64 participants competed in a single-elimination tournament. Saliva samples of all players were obtained before and after the games for the assessment of cortisol levels. The cognitive performances of the players were also assessed by paced auditory serial addition test. Moreover, the electroencephalogram recording was conducted during the games.Results:The results showed that salivary cortisol levels significantly decreased after playing both games. Also, playing the football game increased reaction time, whereas decreased sustained attention and mental fatigue.Conclusion:Conversely, following playing a violent game, the reaction time decreased, and sustained attention and mental fatigue increased. Furthermore, the results of the EEG recording revealed that playing a violent game engaged more brain regions than the football game. In conclusion, playing violent game more effectively improved cognitive performances in the players than the football game.

Sistem Pelacakan Objek Menggunakan Kombinasi Algoritma Optical Flow dan Template Matching

This study aimed to develop a tracking system algorithm by combining optical flow and template matching algorithms to strengthen tracking and minimize the resulting errors. The system has been tested on a football video game with the ball as a tracking object. The optical flow and template matching algorithms are used interchangeably based on the coordinates of both ranges calculated using the Euclidean distance equation. The result shows that the system is able to do tracking, although it is temporarily blocked by other objects, more stable and the distance error between the coordinates of the tracking result and the actual coordinates is not more than 110 pixels compared to using only optical flow or template matching algorithm.

Player Detection based on Support Vector Machine in Football Videos

Player Detection based on Support Vector Machine in Football Videos

Automatic analysis of broadcast football videos using contextual priors

The presence of standard video editing practices in broadcast sports videos, like football, effectively means that such videos have stronger contextual priors than most generic videos. In this paper, we show that such information can be harnessed for automatic analysis of sports videos. Specifically, given an input video, we output per-frame information about camera angles and the events (goal, foul, etc.). Our main insight is that in the presence of temporal context (camera angles) for a video, the problem of event tagging (fouls, corners, goals, etc.) can be cast as per frame multi-class classification problem. We show that even with simple classifiers like linear SVM, we get significant improvement in the event tagging task when contextual information is included. We present extensive results for 10 matches from the recently concluded Football World Cup, to demonstrate the effectiveness of our approach.

Team activity recognition in Association Football using a Bag-of-Words-based method

In this paper, a new methodology is used to perform team activity recognition and analysis in Association Football. It is based on pattern recognition and machine learning techniques. In particular, a strategy based on the Bag-of-Words (BoW) technique is used to characterize short Football video clips that are used to explain the team’s performance and to train advanced classifiers in automatic recognition of team activities. In addition to the neural network-based classifier, three more classifier families are tested: the k-Nearest Neighbor, the Support Vector Machine and the Random Forest. The results obtained show that the proposed methodology is able to explain the most common movements of a team and to perform the team activity recognition task with high accuracy when classifying three Football actions: Ball Possession, Quick Attack and Set Piece. Random Forest is the classifier obtaining the best classification results.

アメリカンフットボール映像におけるプレー開始・終了位置と選手動作情報を用いたボール軌跡抽出

アメリカンフットボール映像におけるプレー開始・終了位置と選手動作情報を用いたボール軌跡抽出

Football Extraction Method Based on Image Segmentation Algorithm

This paper proposes a football object extraction method based on image segmentation algorithm in football video. The football segmentation Interactive operation method with the advantages of high accuracy segmentation, can be applied to other ball games Object (such as volleyball, soccer) segmentation and extraction. In the next step of the study, in a Step to improve the extraction method of the football video frames in image segmentation accuracy ,Application of football and the extracted from football video segment retrieval system for target tracking, to provide an effective method for basketball video clip retrieval.

Is the Unauthorized Use of Former Collegiate Student-Athletes' 'Likeness' a Violation of Their Right of Publicity?

This article analyzes three high-profile lawsuits brought by former National Collegiate Athletic Association (NCAA) student-athletes Ed O'Bannon (O’Bannon v. NCAA, Collegiate Licensing Committee (CLC) and Electronic Arts Incorporated (EA); Sam Keller (Keller v. NCAA, CLC, and EA; and Ryan Hart (Hart v. EA). The central question raised by all three cases: does the “likeness” (personal attributes) displayed of the former student-athletes in the NCAA College Football video game (Keller and Hart) and the NCAA College Basketball video game (O'Bannon) without the former collegiate players’ consent, violate their right of publicity? This article discusses how courts have interpreted and developed the violation of the right of publicity tort, and presents a general overview and legal analysis of the three relevant cases. A secondary issue presented in O’Bannon is how the courts will interpret the vague and ambiguous language used in the standard agreement (Student-Athlete Statement Division I Form 08-3a Section IV) that, according to the NCAA, perpetually relinquishes the rights of student-athletes. Whichever way the courts decide, the decision will forever affect the way the NCAA conducts its commercial business.

Gaze Location Prediction for Broadcast Football Video

The sensitivity of the human visual system decreases dramatically with increasing distance from the fixation location in a video frame. Accurate prediction of a viewer's gaze location has the potential to improve bit allocation, rate control, error resilience, and quality evaluation in video compression. Commercially, delivery of football video content is of great interest because of the very high number of consumers. In this paper, we propose a gaze location prediction system for high definition broadcast football video. The proposed system uses knowledge about the context, extracted through analysis of a gaze tracking study that we performed, to build a suitable prior map. We further classify the complex context into different categories through shot classification thus allowing our model to prelearn the task pertinence of each object category and build the prior map automatically. We thus avoid the limitation of assigning the viewers a specific task, allowing our gaze prediction system to work under free-viewing conditions. Bayesian integration of bottom-up features and top-down priors is finally applied to predict the gaze locations. Results show that the prediction performance of the proposed model is better than that of other top-down models that we adapted to this context.

Detecting the Moment of Snap in Real-World Football Videos


 
 
 In recent years, there has been a great increase in the use of web services for the storage, annotation, and sharing of sports video by athletic teams. Most of these web services, however, do not provide enhanced functional- ities to their users that would enable, e.g., faster access to certain video moments, or reduce manual labor in video annotation. One such web service specializes in American football videos, supporting over 13,000 high school and college teams. Its users often need to fast- forward the video to certain moments of snap when the corresponding plays of the football game start. To our knowledge, this paper describes the first effort toward automating this enhanced functionality. Under a very tight running-time budget, our approach reliably detects the start of a play in an arbitrary football video with minimal assumptions about the scene, viewpoint, video resolution and shot quality. We face many challenges that are rarely addressed by a typical computer vision system, such as, e.g., a wide range of camera viewing angles and distances, and poor resolution and lighting conditions. Extensive empirical evaluation shows that our approach is very close to being usable in a real- world setting.
 
 

Trash talk in a competitive setting: Impact on self‐efficacy and affect

AbstractThe effects of trash talk and competition outcome on self‐efficacy and affect were examined in 40 Madden™ NFL 08 football video game players randomly assigned to two conditions: silence talk, where they played the first game in complete silence; and the second trash talking. Measures of self‐efficacy, positive affect (PA), and negative affect (NA) were administered. Results revealed that players enforced to be silent in the first game instantaneously exhibited lower self‐efficacy, lower PA, and higher NA than players permitted to talk in Game 1. However, players subsequently instructed to remain silent in the second game showed markedly decreased self‐efficacy compared to players permitted to talk in Game 2. Results are interpreted in light of the social‐cognitive‐motivational theory.

Segmentation of Football Video Broadcast

Abstract In this paper a novel segmentation system for football player detection in broadcasted video is presented. Proposed detection system is a complex solution incorporating a dominant color based segmentation technique of a football playfield, a 3D playfield modeling algorithm based on Hough transform and a dedicated algorithm for player tracking, player detection system based on the combination of Histogram of Oriented Gradients (HOG) descriptors with Principal Component Analysis (PCA) and linear Support Vector Machine (SVM) classification. For the shot classification the several classification technique SVM, artificial neural network and Linear Discriminant Analysis (LDA) are used. Evaluation of the system is carried out using HD (1280×720) resolution test material. Additionally, performance of the proposed system is tested with different lighting conditions (including non-uniform pith lightning and multiple player shadows) and various camera positions. Experimental results presented in this paper show that combination of these techniques seems to be a promising solution for locating and segmenting objects in a broadcasted video.

Football bars: urban sub-Saharan Africa's trans-local ‘stadiums’

The sub-Saharan African television landscape has significantly changed since the 1990s under the influence of technological, economic and political factors. Transnational television broadcasting blossomed in Africa and paved the way for the import of overseas football content. Live broadcasting of football flourished due to deregulation and political factors, allowing European football games to become accessible to fans across sub-Saharan Africa. Trans-local ‘stadiums’, football bars, specialised football video theatres and households with cable or satellite subscriptions mediate these processes of trans-localisation. This article argues that football transnational television broadcasting is generating a new form of fandom in sub-Saharan Africa. For many young football fans, transnational football broadcasting is becoming the main or almost only experience of live football. The discussion in this article analyses the emergence and shaping of the trans-local ‘stadiums’, and their attendees.

Personalized Sports Video Customization Using Content and Context Analysis

We present an integrated framework on personalized sports video customization, which addresses three research issues: semantic video annotation, personalized video retrieval and summarization, and system adaptation. Sports video annotation serves as the foundation of the video customization system. To acquire detailed description of video content, external web text is adopted to align with the related sports video according to their semantic correspondence. Based on the derived semantic annotation, a user-participant multiconstraint 0/1 Knapsack model is designed to model the personalized video customization, which can unify both video retrieval and summarization with different fusion parameters. As a measure to make the system adaptive to the particular user, a social network based system adaptation algorithm is proposed to learn latent user preference implicitly. Both quantitative and qualitative experiments conducted on twelve broadcast basketball and football videos validate the effectiveness of the proposed method.

Sports Video Mining via Multichannel Segmental Hidden Markov Models

We study sports video mining as a machine learning and statistical inference problem. We focus on mid-level semantic structures that can serve as building blocks for high-level semantic analysis. Particularly, we are interested in how to infer multiple coexistent structures jointly. We present a new multichannel segmental hidden Markov model (MCSHMM) that is a unique probabilistic graphical model with two advantages. One is the integration of both hierarchical and parallel dynamic structures that offers more flexibility and capacity of capturing the interaction between multiple Markov chains. The other is the incorporation of the segmental HMM (SHMM) to deal with variable-length observations. In addition, we develop a maximum a posteriori (MAP) estimator to optimize the model structure and parameters simultaneously. The proposed MCSHMM is used for American football video analysis. The experiment result shows that the MCSHMM outperforms existing HMMs and has potential to be extended for other video mining tasks.

Personalized Abstraction of Broadcasted American Football Video by Highlight Selection

Video abstraction is defined as creating shorter video clips or video posters from an original video stream. In this paper, we propose a method of generating a personalized abstract of broadcasted American football video. We first detect significant events in the video stream by matching textual overlays appearing in an image frame with the descriptions of gamestats in which highlights of the game are described. Then, we select highlight shots which should be included in the video abstract from those detected events reflecting on their significance degree and personal preferences, and generate a video clip by connecting the shots augmented with related audio and text. An hour-length video can be compressed into a minute-length personalized abstract. We experimentally verified the effectiveness of this method by comparing man-made video abstracts.