A Graph Transduction Game for Multi-target Tracking
This addresses multi-target tracking for video surveillance, but it is incremental as it adapts an existing graph transduction method to this domain.
The paper tackles the problem of multiple people tracking in video surveillance by applying a graph transduction game-theoretic approach, achieving satisfactory results with robustness to imbalanced labeled and unlabeled data.
Semi-supervised learning is a popular class of techniques to learn from labeled and unlabeled data. The paper proposes an application of a recently proposed approach of graph transduction that exploits game theoretic notions to the problem of multiple people tracking. Within the proposed framework, targets are considered as players of a multi-player non-cooperative game. The equilibria of the game is considered as a consistent labeling solution and thus an estimation of the target association in the sequence of frames. Patches of persons are extracted from the video frames using a HOG based detector and their similarity is modeled using distances among their covariance matrices. The solution we propose achieves satisfactory results on video surveillance datasets. The experiments show the robustness of the method even with a heavy unbalance between the number of labeled and unlabeled input patches.