Developed for the Dell/NVIDIA Hackathon 2026
Aegis Guardian leverages edge AI to provide real-time safety monitoring for the elderly without compromising their privacy.
- Fall Detection: Real-time spatial analysis of human biomechanics.
- Privacy Mode: Processes raw video at the edge and displays only anonymized "skeleton" data.
- Hardware Accelerated: Optimized for the NVIDIA GB10 (Blackwell) architecture.
- Hardware: Dell Pro Max 10GB | NVIDIA GB10 GPU
- AI Models: YOLOv8-Pose (Medium)
- Library: PyTorch (CUDA 12.1), OpenCV, Ultralytics
- Inference Latency:
- Throughput:
- Precision:
- Clone the repo:
git clone https://github.com/qiyahuang72/caregiver_ai.git - Enter directory:
cd caregiver_ai - Setup Venv:
python3 -m venv venv && source venv/bin/activate - Install Deps:
pip install -r requirements.txt - Run Demo:
python guardian.py