Result Details
Dynamic People Counting from Delay-Doppler Images in Challenging Scenarios: Enhancing Model Performance
Maršálek Roman, prof. Ing., Ph.D., UREL (FEEC)
This study presents a novel radar-based people
counting (PCnt) methodology empowered by deep learning (DL)
frameworks. The challenges we face include overfitting due to
the model’s tendency to extract highly domain-specific features.
These challenges arise from limited data and clutter in indoor
settings. To tackle this, our radar system operates in both lab
and industrial environments. We propose a 2D-CNN approach
and explore ways to handle these challenges, focusing on im
proving accuracy through preprocessing techniques. Additionally,
we introduced data augmentation strategies to enhance model
robustness and mitigate overfitting. Our experiments show our
approach accurately counts people moving along the radar line in
various environments. However, detecting stationary individuals
and distinguishing between moving human and non-human
entities remain challenging areas for future work.
People counting; heterogeneous clutter environment; preprocessing; data augmentation; deep learning.
@inproceedings{BUT188392,
author="Malek Abdulmalek Ahmed {Ali} and Roman {Maršálek}",
title="Dynamic People Counting from Delay-Doppler Images in Challenging Scenarios: Enhancing Model Performance",
booktitle="RADIOELEKTRONIKA 2024: 2024 34th International Conference Radioelektronika",
year="2024",
pages="6",
publisher="Institute of Electrical and Electronics Engineers Inc.",
doi="10.1109/RADIOELEKTRONIKA61599.2024.10524098",
isbn="979-8-3503-6215-2",
url="https://ieeexplore.ieee.org/document/10524098"
}