mmCounter: Static People Counting in Dense Indoor Scenarios Using mmWave Radar

TL;DR

mmCounter is a novel radar-based system that accurately counts static people in dense indoor environments by detecting subtle body movements like breathing, overcoming limitations of traditional radar methods that rely on movement.

Contribution

The paper introduces mmCounter, a new signal processing pipeline that detects ultra-low frequency signals to count static individuals using mmWave radar, a significant advancement over existing methods.

Findings

Achieves 87% F1 score in familiar environments

Maintains 60% F1 score in new environments

Counts up to seven people in a three-square-meter space

Abstract

mmWave radars struggle to detect or count individuals in dense, static (non-moving) groups due to limitations in spatial resolution and reliance on movement for detection. We present mmCounter, which accurately counts static people in dense indoor spaces (up to three people per square meter). mmCounter achieves this by extracting ultra-low frequency (< 1 Hz) signals, primarily from breathing and micro-scale body movements such as slight torso shifts, and applying novel signal processing techniques to differentiate these subtle signals from background noise and nearby static objects. Our problem differs significantly from existing studies on breathing rate estimation, which assume the number of people is known a priori. In contrast, mmCounter utilizes a novel multi-stage signal processing pipeline to extract relevant low-frequency sources along with their spatial information and map these sources to individual people, enabling accurate counting. Extensive evaluations in various environments demonstrate that mmCounter delivers an 87% average F1 score and 0.6 mean absolute error in familiar environments, and a 60% average F1 score and 1.1 mean absolute error in previously untested environments. It can count up to seven individuals in a three square meter space, such that there is no side-by-side spacing and only a one-meter front-to-back distance.