Multi-Person tracking by multi-scale detection in Basketball scenarios
This work addresses the problem of frequent occlusions and cluttering in basketball scenarios for teams seeking performance insights through tracking data, representing an incremental improvement in domain-specific methods.
The paper tackles multi-person tracking in single-camera basketball videos by proposing a novel multi-scale detection method combined with geometric and content features, achieving notable results in detection (F1-score) and tracking (MOTA) metrics on a custom dataset of over 10k bounding boxes.
Tracking data is a powerful tool for basketball teams in order to extract advanced semantic information and statistics that might lead to a performance boost. However, multi-person tracking is a challenging task to solve in single-camera video sequences, given the frequent occlusions and cluttering that occur in a restricted scenario. In this paper, a novel multi-scale detection method is presented, which is later used to extract geometric and content features, resulting in a multi-person video tracking system. Having built a dataset from scratch together with its ground truth (more than 10k bounding boxes), standard metrics are evaluated, obtaining notable results both in terms of detection (F1-score) and tracking (MOTA). The presented system could be used as a source of data gathering in order to extract useful statistics and semantic analyses a posteriori.