The GUI of HOOD allows users to follow the prediction, indicating the presence of one or multiple persons in the room with/without moving or stationary clutters through the "Human in the room" visual effect.
Detecting human presence indoors with millimeter-wave frequency-modulated continuous-wave (FMCW) radar faces challenges from both moving and stationary clutter. This work proposes a robust and real-time capable human presence and out-of-distribution (OOD) detection method using 60 GHz short-range FMCW radar. HOOD solves the human presence and OOD detection problems simultaneously in a single pipeline. Our solution relies on a reconstruction-based architecture and works with radar macro and micro range-Doppler images (RDIs). HOOD aims to accurately detect the presence of humans in the presence or absence of moving and stationary disturbers. Since HOOD is also an OOD detector, it aims to detect moving or stationary clutters as OOD in humans' absence and predicts the current scene's output as “no presence." HOOD performs well in diverse scenarios, demonstrating its effectiveness across different human activities and situations. On our dataset collected with a 60 GHz short-range FMCW radar, we achieve an average AUROC of 94.36%. Additionally, our extensive evaluations and experiments demonstrate that HOOD outperforms state-of-the-art (SOTA) OOD detection methods in terms of common OOD detection metrics. Importantly, HOOD also perfectly fits on Raspberry Pi 3B+ with an ARM Cortex-A53 CPU, which showcases its versatility across different hardware environments.
The GUI of HOOD allows users to follow the prediction, indicating the presence of one or multiple persons in the room with/without moving or stationary clutters through the "Human in the room" visual effect.
The GUI of HOOD enables users to track the prediction, indicating the absence of any human presence in the room while there may be some moving or stationary clutters, portrayed by the "No human in the room" visual effect.
We have prior works that are relevant to our current study:
MCROOD: Multi-Class Radar Out-of-Distribution Detection proposes a reconstruction-based multi-class OOD detector for radar range Doppler images (RDIs). The detector aims to classify any moving object other than a person sitting, standing, or walking as OOD. It also includes a respiration detector (RESPD) for detecting minor human body movements like breathing.
Reconstruction-based Out-of-Distribution Detection for Short-Range FMCW Radar proposes a novel reconstruction-based OOD detector designed for the radar domain. Our method utilizes an autoencoder (AE) and its latent representation to detect OOD samples. We introduce patch-based reconstruction loss and energy values from latent representations as scores.
@article{,
author = {},
title = {},
journal = {},
year = {},
}