Online Learned Player Recognition Model Based Soccer Player Tracking and Labeling for Long-Shot Scenes

Abstract

SUMMARYSoccer player tracking and labeling suffer from the similar appearance of the players in the same team, especially in long-shot scenes where the faces and the numbers of the players are too blurry to identify. In this paper, we propose an efficient multi-player tracking system. The tracking system takes the detection responses of a human detector as inputs. To realize real-time player detection, we generate a spatial proposal to minimize the scanning scope of the detector. The tracking system utilizes the discriminative appearance models trained using the online Boosting method to reduce data-association ambiguity caused by the appearance similarity of the players. We also propose to build an online learned player recognition model which can be embedded in the tracking system to approach online player recognition and labeling in tracking applications for long-shot scenes by two stages. At the first stage, to build the model, we utilize the fast k-means clustering method instead of classic k-means clustering to build and update a visual word vocabulary in an efficient online manner, using the informative descriptors extracted from the training samples drawn at each time step of multi-player tracking. The first stage finishes when the vocabulary is ready. At the second stage, given the obtained visual word vocabulary, an incremental vector quantization strategy is used to recognize and label each tracked player. We also perform importance recognition validation to avoid mistakenly recognizing an outlier, namely, people we do not need to recognize, as a player. Both quantitative and qualitative experimental results on the long-shot video clips of a real soccer game video demonstrate that, the proposed player recognition model performs much better than some state-of-the-art online learned models, and our tracking system also performs quite effectively even under very complicated situations.

Visualization of Football Tactics with Deep Learning Models

“…The picture taken by the former was in a fixed scene, so the background was unchanged or only slightly changed; the picture taken by the latter was in a dynamic scene, and the lens was always following the target area of interest for shooting, so its background was changing. Reference [10,11] installed 4 fixed cameras on one side of the field, and reference [12] installed 6 fixed cameras evenly distributed on both sides of the field, using the background subtraction method to detect players. The video shot by the moving camera usually referred to the live football video on the TV.…”

Light Cascaded Convolutional Neural Networks for Accurate Player Detection

“…To make player detection more robust, researchers have developed stronger features such as histogram of oriented gradients (HOG) features [20] with the support vector machine (SVM) method [21,22]. Moreover, researchers have combined different features such as edge [23], LBP [24] and motion [25] or have employed part-based model [26,27] to improve performance. However, they are not as robust as deep learning based methods in general.…”