Exploring Local Context for Multi-target Tracking in Wide Area Aerial Surveillance
This addresses tracking discontinuities in aerial surveillance for applications like event understanding, but it is incremental as it builds on existing detection association methods.
The paper tackles the problem of tracking many vehicles in wide area aerial imagery, where slow or stopped vehicles cause long-term missing detections and tracking discontinuities, by coupling detection association with a local context tracker that uses graph optimization and flow hypotheses, resulting in significant improvement over state-of-the-art methods.
Tracking many vehicles in wide coverage aerial imagery is crucial for understanding events in a large field of view. Most approaches aim to associate detections from frame differencing into tracks. However, slow or stopped vehicles result in long-term missing detections and further cause tracking discontinuities. Relying merely on appearance clue to recover missing detections is difficult as targets are extremely small and in grayscale. In this paper, we address the limitations of detection association methods by coupling it with a local context tracker (LCT), which does not rely on motion detections. On one hand, our LCT learns neighboring spatial relation and tracks each target in consecutive frames using graph optimization. It takes the advantage of context constraints to avoid drifting to nearby targets. We generate hypotheses from sparse and dense flow efficiently to keep solutions tractable. On the other hand, we use detection association strategy to extract short tracks in batch processing. We explicitly handle merged detections by generating additional hypotheses from them. Our evaluation on wide area aerial imagery sequences shows significant improvement over state-of-the-art methods.