Single View Physical Distance Estimation using Human Pose

TL;DR

This paper introduces a fully automated system for estimating physical distances from a single RGB image by leveraging human pose priors, enabling applications like social distancing without dedicated calibration.

Contribution

It presents a novel pose-based auto-calibration method that estimates camera parameters and distances from a single image, achieving state-of-the-art results and providing a new benchmark dataset.

Findings

State-of-the-art performance on public datasets

Enables distance measurement without dedicated calibration

Introduces MEVADA, a new evaluation benchmark

Abstract

We propose a fully automated system that simultaneously estimates the camera intrinsics, the ground plane, and physical distances between people from a single RGB image or video captured by a camera viewing a 3-D scene from a fixed vantage point. To automate camera calibration and distance estimation, we leverage priors about human pose and develop a novel direct formulation for pose-based auto-calibration and distance estimation, which shows state-of-the-art performance on publicly available datasets. The proposed approach enables existing camera systems to measure physical distances without needing a dedicated calibration process or range sensors, and is applicable to a broad range of use cases such as social distancing and workplace safety. Furthermore, to enable evaluation and drive research in this area, we contribute to the publicly available MEVA dataset with additional distance annotations, resulting in MEVADA -- the first evaluation benchmark in the world for the pose-based auto-calibration and distance estimation problem.