用边缘设备实现高精度实时人流计数，应急时更可靠。
Real-Time AI-Driven People Tracking and Counting Using Overhead Cameras
- 融合新跟踪算法、计数算法与优化检测模型
- 在低功耗设备上达97%准确率，帧率20-27FPS
- 适合智能建筑与交通系统中的实时人流监控
智能建筑与智能交通系统中精准的人流计数对能源管理、安全规程和资源分配至关重要，尤其在紧急情况下，精确的人员数量对安全疏散极为关键。现有方法在大客流场景下表现不佳，即使增加少数几人也会导致精度下降。为此，本研究提出一种新方法，结合新型目标跟踪算法、新型计数算法以及微调后的目标检测模型，在低功耗边缘计算设备上实现了97%的实时人流计数准确率，帧率为20-27 FPS。
原文摘要 · Abstract (English)
Accurate people counting in smart buildings and intelligent transportation systems is crucial for energy management, safety protocols, and resource allocation. This is especially critical during emergencies, where precise occupant counts are vital for safe evacuation. Existing methods struggle with large crowds, often losing accuracy with even a few additional people. To address this limitation, this study proposes a novel approach combining a new object tracking algorithm, a novel counting algorithm, and a fine-tuned object detection model. This method achieves 97% accuracy in real-time people counting with a frame rate of 20-27 FPS on a low-power edge computer.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。