Ben Salah, Mohamed Khalil, Jouvet, Philippe et Noumeir, Rita.
2025.
« PICU face and thoracoabdominal detection using self-supervised divided space–time mamba ».
Life, vol. 15, nº 11.
Prévisualisation |
PDF
Noumeir-R-2025-33122.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY. Télécharger (25MB) | Prévisualisation |
Résumé
Non-contact vital sign monitoring in Pediatric Intensive Care Units is challenged by frequent occlusions, data scarcity, and the need for temporally stable anatomical tracking to extract reliable physiological signals. Traditional detectors produce unstable tracking, while video transformers are too computationally intensive for deployment on resource-limited clinical hardware. We introduce Divided Space–Time Mamba, an architecture that decouples spatial and temporal feature learning using State Space Models to achieve linear-time complexity, over 92% lower than standard transformers. To handle data scarcity, we employ self-supervised pre-training with masked autoencoders on over 50 k domain-specific video clips and further enhance robustness with multimodal RGB-D input. Our model demonstrates superior performance, achieving 0.96 mAP@0.5, 0.62 mAP50-95, and 0.95 rotated IoU. Operating at 23 FPS (43 ms latency), our method is approximately 1.9× faster than VideoMAE and 5.7× faster than frame-wise YOLOv8, demonstrating its suitability for real-time clinical monitoring.
| Type de document: | Article publié dans une revue, révisé par les pairs |
|---|---|
| Professeur: | Professeur Noumeir, Rita |
| Affiliation: | Génie électrique |
| Date de dépôt: | 17 déc. 2025 15:24 |
| Dernière modification: | 10 janv. 2026 16:41 |
| URI: | https://espace2.etsmtl.ca/id/eprint/33122 |
Actions (Authentification requise)
 |
Dernière vérification avant le dépôt |