Long-Range Trajectories from Global and Local Motion Representations
This work addresses motion representation for human activity tasks like motion segmentation, but it appears incremental as it builds on existing trajectory and flow methods.
The paper tackles the problem of representing motion in videos for scene analysis and human activity understanding by proposing a system that integrates local and global motion features to generate long-range trajectories. The results demonstrate its applicability across different scenarios, with trajectories compared to manual annotations of individual pedestrians.
Motion is a fundamental cue for scene analysis and human activity understan- ding in videos. It can be encoded in trajectories for tracking objects and for action recognition, or in form of flow to address behaviour analysis in crowded scenes. Each approach can only be applied on limited scenarios. We propose a motion-based system that represents the spatial and temporal features of the flow in terms of long-range trajectories. The novelty resides on the system formulation, its generic approach to handle scene variability and motion variations, motion integration from local and global representations, and the resulting long-range trajectories that overcome trajectory-based approach problems. We report the results and conclusions that state its pertinence on different scenarios, comparing and correlating the extracted trajectories of individual pedestrians, manually annotated. We also propose an evaluation framework and stress the diverse system characteristics that can be used for human activity tasks, namely on motion segmentation.