AI-Based Human Detection in Indoor Environments using IR-UWB Radar
This paper is built on a previously developed IRUWB radar-based detection approach for industrial indoor environments. The proposed signal processing steps resulted in range-Doppler maps of moving objects and humans, which are classified using machine/deep learning algorithms. We evaluate the performance of Support Vector Machines (SVM) and three convolutional neural network (CNN) architectures-AlexNet, GoogLeNet, and ResNet-18-across various signal-to-noise ratio (SNR) levels. Their effectiveness, assessed in terms of correct classification rate (CCR) and confusion matrix, is compared and discussed in the paper.
Authors
- Emanuel Rădoi (ORCID: https://orcid.org/0000-0002-0819-6285)
- Roua Youssef (ORCID: https://orcid.org/0000-0002-9852-4149)
- Stéphane Azou (ORCID: https://orcid.org/0000-0001-8185-7134)
- Zaynab Baydoun (ORCID: https://orcid.org/0000-0003-4976-3482)
- Tina Yaacoub
Institutions
- Centre National de la Recherche Scientifique (FR)
- Université de Bretagne Occidentale (FR)
- École nationale d'ingénieurs de Brest (FR)
- Saint Joseph University (LB)
- Institut d'Électronique et des Technologies du numéRique (FR)
- Laboratoire des Sciences et Techniques de l’Information de la Communication et de la Connaissance (FR)
- Université de Rennes (FR)
Publication Details
- Published
- 2025-06-23
- DOI
- https://doi.org/10.1109/ic_etc65981.2025.11141102
- Primary Topic
- Advanced SAR Imaging Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00