Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset

TL;DR

This paper introduces MVP-Occ, a synthetic dataset for dense multi-view pedestrian occupancy prediction, and proposes OmniOcc, a model that predicts voxel occupancy and scene labels from multi-view images.

Contribution

The paper presents a new synthetic dataset MVP-Occ and a baseline model OmniOcc for multi-view pedestrian occupancy prediction in urban scenes.

Findings

MVP-Occ enables detailed pedestrian occupancy analysis in large-scale scenes.

OmniOcc effectively predicts voxel occupancy and semantic labels from multi-view images.

The model's components are validated through comprehensive analysis.

Abstract

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.