Montoliu Raúl, Martín-Félez Raúl, Torres-Sospedra Joaquín, Martínez-Usó Adolfo
Institute of New Imaging Technologies (INIT), Jaume I University, Castellón, Spain.
Hum Mov Sci. 2015 Jun;41:165-78. doi: 10.1016/j.humov.2015.03.007. Epub 2015 Mar 25.
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.
在本文中，一种新方法被用于在英式足球中进行团队活动识别与分析。它基于模式识别和机器学习技术。具体而言，一种基于词袋（BoW）技术的策略被用于刻画用于解释球队表现的简短足球视频片段，并训练用于自动识别团队活动的先进分类器。除了基于神经网络的分类器外，还测试了另外三个分类器家族：k近邻、支持向量机和随机森林。所得结果表明，所提出的方法能够解释球队最常见的动作，并在对三种足球动作：控球、快速进攻和定位球进行分类时以高精度执行团队活动识别任务。随机森林是获得最佳分类结果的分类器。
