ANTHROPOS-V: benchmarking the novel task of Crowd Volume Estimation

2025-01-03

AI Summary

This paper introduces Crowd Volume Estimation (CVE), a novel task that estimates the total 3D body volume of all individuals in a scene from a single RGB image—enabling applications in event management, public safety, and infrastructure load assessment. To support CVE, we present ANTHROPOS-V, the first synthetic video benchmark with per-person 3D volumetric annotations, including SMPL parameters, 2D/3D keypoints, and photorealistic crowd distributions. Methodologically, we propose an end-to-end framework integrating SMPL-based anatomical priors, Human Mesh Recovery (HMR), crowd-counting features, and a lightweight volume regression network. Experiments demonstrate that our approach significantly outperforms state-of-the-art human mesh reconstruction and crowd counting baselines on synthetic data; predicted volume distributions align with real-world demographic statistics; and the model exhibits robust cross-domain generalization to real-world images. This work formally defines the CVE task, releases the first 3D volume-annotated crowd video benchmark, and provides a dedicated, effective solution.

Technology Category

• Computer Vision: 3D Computer Vision
• Humans and AI: Crowd Sourcing and Human Computation
• Intelligent Robots: State Estimation

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

We introduce the novel task of Crowd Volume Estimation (CVE), defined as the process of estimating the collective body volume of crowds using only RGB images. Besides event management and public safety, CVE can be instrumental in approximating body weight, unlocking weight sensitive applications such as infrastructure stress assessment, and assuring even weight balance. We propose the first benchmark for CVE, comprising ANTHROPOS-V, a synthetic photorealistic video dataset featuring crowds in diverse urban environments. Its annotations include each person's volume, SMPL shape parameters, and keypoints. Also, we explore metrics pertinent to CVE, define baseline models adapted from Human Mesh Recovery and Crowd Counting domains, and propose a CVE specific methodology that surpasses baselines. Although synthetic, the weights and heights of individuals are aligned with the real-world population distribution across genders, and they transfer to the downstream task of CVE from real images. Benchmark and code are available at github.com/colloroneluca/Crowd-Volume-Estimation.

Problem

• Crowd Body Volume Estimation
• Public Safety
• Event Management

Innovation

• Crowd Volume Estimation
• ANTHROPOS-V Dataset
• Advanced CVE Methodology