论文标题
REALHEPONET：野外头部姿势估算的强大单阶段convnet
RealHePoNet: a robust single-stage ConvNet for head pose estimation in the wild
论文作者
论文摘要
图像中的人头姿势估计在许多领域都有应用，例如人类计算机的互动或视频监视任务。在这项工作中，我们通过使用单个卷积神经网络（Convnet）模型来解决此问题，以此定义为垂直（倾斜/俯仰）和水平（PAN/YAW）角度的估计，试图平衡精度和推理速度，以使其在现实世界应用中最大化其可用性。我们的模型在两个数据集的组合中进行了训练：“指向” 04'（旨在涵盖各种姿势）和“野生中的带注释的面部标志”（为了提高模型的稳健性，以用于现实世界图像）。合并数据集的三个不同分区定义并用于培训，验证和测试目的。这项工作的结果是，我们获得了经过训练的Convnet模型，即构成的Realheponet，鉴于低分辨率的灰度输入图像，而无需使用面部地标，可以估算出低误差倾斜和锅角（测试分区中的平均误差率为4.4°））。另外，鉴于其推理时间较低（每头〜6 ms），我们即使与中等规格的硬件配对（即GTX 1060 GPU），我们也可以考虑使用模型。 *代码可在：https：//github.com/rafabs97/headpose_final *演示视频：https：//www.youtube.com/watch?v=2ueuxh5djae
Human head pose estimation in images has applications in many fields such as human-computer interaction or video surveillance tasks. In this work, we address this problem, defined here as the estimation of both vertical (tilt/pitch) and horizontal (pan/yaw) angles, through the use of a single Convolutional Neural Network (ConvNet) model, trying to balance precision and inference speed in order to maximize its usability in real-world applications. Our model is trained over the combination of two datasets: 'Pointing'04' (aiming at covering a wide range of poses) and 'Annotated Facial Landmarks in the Wild' (in order to improve robustness of our model for its use on real-world images). Three different partitions of the combined dataset are defined and used for training, validation and testing purposes. As a result of this work, we have obtained a trained ConvNet model, coined RealHePoNet, that given a low-resolution grayscale input image, and without the need of using facial landmarks, is able to estimate with low error both tilt and pan angles (~4.4° average error on the test partition). Also, given its low inference time (~6 ms per head), we consider our model usable even when paired with medium-spec hardware (i.e. GTX 1060 GPU). * Code available at: https://github.com/rafabs97/headpose_final * Demo video at: https://www.youtube.com/watch?v=2UeuXh5DjAE
