Recurrent Autoregressive Networks for Online Multi-Object Tracking
This work addresses the problem of reliable object tracking in crowded and occluded scenes for computer vision applications, representing an incremental improvement with a novel hybrid method.
The paper tackles the challenge of online multi-object tracking by proposing the Recurrent Autoregressive Network (RAN), a temporal generative modeling framework that uses external and internal memory to associate object trajectories with detections, achieving top-ranked results on MOT 2015 and 2016 benchmarks.
The main challenge of online multi-object tracking is to reliably associate object trajectories with detections in each video frame based on their tracking history. In this work, we propose the Recurrent Autoregressive Network (RAN), a temporal generative modeling framework to characterize the appearance and motion dynamics of multiple objects over time. The RAN couples an external memory and an internal memory. The external memory explicitly stores previous inputs of each trajectory in a time window, while the internal memory learns to summarize long-term tracking history and associate detections by processing the external memory. We conduct experiments on the MOT 2015 and 2016 datasets to demonstrate the robustness of our tracking method in highly crowded and occluded scenes. Our method achieves top-ranked results on the two benchmarks.