There is an increasing demand for lightweight multi-person pose estimation for many emerging smart IoT applications. However, the existing algorithms tend to have large model sizes and intense computational requirements, making them ill-suited for real-time applications and deployment on resource-constrained hardware. Lightweight and real-time approaches are exceedingly rare and come at the cost of inferior accuracy. In this paper, we present EfficientHRNet, a family of lightweight multi-person human pose estimators that are able to perform in real-time on resource-constrained devices. By unifying recent advances in model scaling with high-resolution feature representations, EfficientHRNet creates highly accurate models while reducing computation enough to achieve real-time performance. The largest model is able to come within 4.4% accuracy of the current state-of-the-art, while having 1/3 the model size and 1/6 the computation, achieving 23 FPS on Nvidia Jetson Xavier. Compared to the top real-time approach, EfficientHRNet increases accuracy by 22% while achieving similar FPS with \(\frac{1}{3}\) the power. At every level, EfficientHRNet proves to be more computationally efficient than other bottom-up 2D human pose estimation approaches, while achieving highly competitive accuracy.

许多新兴的智能物联网应用对轻量级多人姿势估计的需求不断增加。然而，现有算法往往具有较大的模型尺寸和强烈的计算要求，使得它们不适合在资源受限的硬件上的实时应用和部署。轻量级和实时的方法非常罕见，并且以较低的准确性为代价。在本文中，我们提出了 EfficientHRNet，这是一个轻量级的多人人体姿势估计器系列，能够在资源受限的设备上实时执行。通过将模型缩放的最新进展与高分辨率特征表示相结合，EfficientHRNet 创建了高度准确的模型，同时减少了足以实现实时性能的计算量。最大的模型能够在4以内。当前最先进技术的 4% 准确度，同时模型大小是 1/3，计算是 1/6，在 Nvidia Jetson Xavier 上实现了 23 FPS。与顶级实时方法相比，EfficientHRNet 将准确率提高了 22%，同时实现了类似的 FPS\(\frac{1}{3}\)幂。在各个层面上，EfficientHRNet 被证明比其他自下而上的 2D 人体姿态估计方法在计算上更高效，同时实现了极具竞争力的准确性。