Background and Objective: Falls among elderly people can cause serious injury and reduce quality of life. Timely prediction and detection are essential to prevent harm and support well-being. We propose a portable, low-power, battery-operated, vision-based fall prediction and detection system using HPE on an AMD Kria K26 System-on-Module (SOM). The objective is a non-intrusive, privacy-preserving system for real-time fall detection. Methods: The system uses an Intel RealSense D455 range-sensing camera connected to the K26 SOM by USB. It captures synchronized RGB and depth frames, 640 x 480 x 3 and 640 x 480 pixels, at 60 FPS. The SOM runs a three-stage pipeline with quantized YOLOX, Anchor-to-Joint (A2J), and fall-detection models. YOLOX identifies human bounding boxes from RGB frames, then discards the RGB frames to preserve privacy. A2J uses depth frames to estimate 15 joint keypoints per person. A CNN uses selected joint coordinates (x, y, z) to classify fall activity. YOLOX was trained on CrowdHuman; A2J on ITOP, MP-3DHP, UR Fall Detection, and a custom SDSU PSG dataset; and the CNN on UR Fall Detection and SDSU PSG. The design used a single-core DPU with a serial pipeline and a dual-core DPU running YOLOX and A2J with multiple threads. Results: Quantized accuracy was evaluated using IoU >= 50% for YOLOX, mAP with a 10-cm rule for A2J, and classification accuracy, (TP + TN)/(TP + TN + FP + FN), for the CNN. Accuracies were 74%, 84.13%, and 75.85%. Throughput improved from 2.5 FPS for the single-threaded pipeline to 4.5 FPS for the multi-threaded version. Conclusion: Results demonstrate the feasibility of privacy-preserving fall detection on an AMD Kria K26 edge device. On-device HPE and fall classification runs without cloud dependency, supporting elderly monitoring and assistive healthcare. Future work will improve model accuracy and speed.

翻译：背景与目标：老年人跌倒可能导致严重伤害并降低生活质量。及时预测和检测对于预防伤害和支持健康至关重要。我们提出了一种便携式、低功耗、电池供电的基于视觉的跌倒预测与检测系统，在AMD Kria K26系统模块（SOM）上使用人体姿态估计（HPE）。目标是实现一种非侵入性、保护隐私的实时跌倒检测系统。方法：系统使用Intel RealSense D455距离感应摄像头，通过USB连接到K26 SOM。该摄像头以60 FPS的帧率捕捉640×480×3像素的同步RGB图像和640×480像素的深度图像。SOM运行一个三阶段流水线，包括量化YOLOX、Anchor-to-Joint（A2J）和跌倒检测模型。YOLOX从RGB帧中识别人体边界框，随后丢弃RGB帧以保护隐私。A2J利用深度帧估计每个人的15个关节关键点。卷积神经网络（CNN）使用选定的关节坐标（x, y, z）对跌倒行为进行分类。YOLOX在CrowdHuman数据集上训练；A2J在ITOP、MP-3DHP、UR Fall Detection和自定义SDSU PSG数据集上训练；CNN在UR Fall Detection和SDSU PSG上训练。设计采用单核DPU串行流水线和双核DPU运行YOLOX与A2J的多线程方案。结果：量化精度通过YOLOX的IoU≥50%评估、A2J的10厘米规则mAP评估，以及CNN的分类准确率（TP+TN）/（TP+TN+FP+FN）评估。准确率分别为74%、84.13%和75.85%。吞吐量从单线程流水线的2.5 FPS提升至多线程版本的4.5 FPS。结论：结果证明了在AMD Kria K26边缘设备上实现隐私保护跌倒检测的可行性。设备端HPE和跌倒分类无需依赖云端即可运行，支持老年人监护和辅助医疗。未来工作将提升模型精度和速度。