中文摘要：

头部姿态估计在人工智能、模式识别及人机智能交互等领域应用广泛。好的头部姿态估计算法应对光照、噪声、身份、遮挡等因素时鲁棒性较好,但目前为止如何提高姿态估计的精确度与鲁棒性依然是计算机视觉领域的一大挑战。提出了一种基于深度学习进行头部姿态估计的方法。利用深度学习强大的学习能力,对输入的人脸图像进行一系列的非线性操作,逐层提取图像中抽象的特征,然后利用提取的特征进行分类。此类特征在姿态上具有较大的差异性,同时对光照、身份、遮挡等因素鲁棒。在CAS-PEAL数据集上对该方法进行了评估实验。实验结果表明,该方法有效地提高了姿态估计的准确性。

英文摘要：

Head pose estimation has been widely used in the field of artificial intelligence, pattern recognition and intelligent human-computer interaction and so on. Good head pose estimation algorithm should deal with light, noise,identity, shelter and other factors robustly, but so far how to improve the accuracy and robustness of attitude estimation remains a major challenge in the field of computer vision. A method based on deep learning for pose estimation is presented. Deep learning with a strong learning ability,it can extract high-level image features of the input image by through a series of non-linear operation, then classifying the input image using the extracted feature. Such characteristics have greater differences in pose, while they are robust of light,identity, occlusion and other factors. The proposed head pose estimation is evaluated on the CAS-PEAL data set. Experimental results show that this method is effective to improve the accuracy of pose estimation.