# Evaluating Crowd Density Estimators via Their Uncertainty Bounds

## TL;DR

This paper introduces a method using Belief Function Theory to evaluate and compare the uncertainty bounds of crowd density estimators across multiple scales, enhancing reliability assessment for crowd monitoring.

## Contribution

It presents a novel approach to quantify and compare the uncertainty bounds of crowd density estimators using Belief Function Theory, enabling better reliability assessment.

## Key findings

- Effective comparison of multi-scale crowd density estimators.
- Characterization of estimator reliability for different prudence levels.
- Enhanced understanding of uncertainty bounds in crowd monitoring.

## Abstract

In this work, we use the Belief Function Theory which extends the probabilistic framework in order to provide uncertainty bounds to different categories of crowd density estimators. Our method allows us to compare the multi-scale performance of the estimators, and also to characterize their reliability for crowd monitoring applications requiring varying degrees of prudence.