Toward Accurate Online Multi-target Multi-camera Tracking in Real-time

Multi-target multi-camera tracking is the task of determining the trajectories of objects within a network of cameras. Besides many others, it is a crucial task, e.g., in traffic analysis or law enforcement. Current research mainly focuses on offline algorithms for cross-camera association, which require all video data at once and often lack real-time capability. Thus, such approaches are unsuitable for tracking a criminal's escape route and enabling immediate intervention and arrest. To close this gap, we introduce a novel online multi-target multi-camera tracking method in this work which integrates spatial-temporal information and applies a new probability-based association metric. Moreover, we prove the real-time capability and significantly outperform the baseline on two datasets. In addition, the performance gap to more complex and slower offline methods is discussed to indicate the current state of research.