Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset
This work addresses pedestrian occupancy prediction for urban traffic applications, but it is incremental as it builds on multi-view pedestrian detection with a new dataset and baseline model.
The paper tackles the problem of predicting pedestrian occupancy in urban traffic by creating a new synthetic dataset called MVP-Occ for dense scenarios and proposing a baseline model, OmniOcc, which achieves predictions of voxel occupancy and panoptic labels from multi-view images.
We address an advanced challenge of predicting pedestrian occupancy as an extension of multi-view pedestrian detection in urban traffic. To support this, we have created a new synthetic dataset called MVP-Occ, designed for dense pedestrian scenarios in large-scale scenes. Our dataset provides detailed representations of pedestrians using voxel structures, accompanied by rich semantic scene understanding labels, facilitating visual navigation and insights into pedestrian spatial information. Furthermore, we present a robust baseline model, termed OmniOcc, capable of predicting both the voxel occupancy state and panoptic labels for the entire scene from multi-view images. Through in-depth analysis, we identify and evaluate the key elements of our proposed model, highlighting their specific contributions and importance.