Towards Robust Human Trajectory Prediction in Raw Videos
This addresses a practical issue for applications like autonomous vehicles and indoor robots by making trajectory prediction more robust to real-world noise, though it is incremental as it builds on existing pipelines.
The paper tackles the problem of human trajectory prediction in raw videos, showing that tracking errors severely degrade accuracy, and proposes a re-tracking algorithm that improves both tracking and prediction performance on public benchmarks.
Human trajectory prediction has received increased attention lately due to its importance in applications such as autonomous vehicles and indoor robots. However, most existing methods make predictions based on human-labeled trajectories and ignore the errors and noises in detection and tracking. In this paper, we study the problem of human trajectory forecasting in raw videos, and show that the prediction accuracy can be severely affected by various types of tracking errors. Accordingly, we propose a simple yet effective strategy to correct the tracking failures by enforcing prediction consistency over time. The proposed "re-tracking" algorithm can be applied to any existing tracking and prediction pipelines. Experiments on public benchmark datasets demonstrate that the proposed method can improve both tracking and prediction performance in challenging real-world scenarios. The code and data are available at https://git.io/retracking-prediction.