Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions
Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions
复制标题
DOI：
10.1109/tip.2017.2654165
复制
发表时间：
2017-03-01
影响因子：
10.6
通讯作者：
Evangelidis, Georgios
中科院分区：
文献类型：
--
作者：
Drouard, Vincent;Horaud, Radu;Evangelidis, Georgios
头姿估计在社会事件分析、人机交互、驾驶辅助等方面有着广泛的应用。头部姿态估计是具有挑战性的，因为它必须应对不断变化的照明条件，面部方向和外观的可变性，面部标志的部分遮挡，以及边界盒到面部的对齐误差。我们建议使用线性回归与部分潜在输出的混合。该回归方法学习将高维特征向量（从人脸的边界框中提取）映射到头部姿态角度和边界框位移的联合空间上，从而在存在不可观察现象的情况下对其进行鲁棒预测。我们详细描述了映射方法，它结合了无监督流形学习技术和混合回归的优点。我们用三个公开可用的数据集验证了我们的方法，并使用几种最先进的头姿估计方法对所提出算法的四个变体进行了全面的基准测试。
Head-pose estimation has many applications, such as social event analysis, human-robot and human-computer interaction, driving assistance, and so forth. Head-pose estimation is challenging, because it must cope with changing illumination conditions, variabilities in face orientation and in appearance, partial occlusions of facial landmarks, as well as bounding-box-to-face alignment errors. We propose to use a mixture of linear regressions with partially-latent output. This regression method learns to map high-dimensional feature vectors (extracted from bounding boxes of faces) onto the joint space of head-pose angles and bounding-box shifts, such that they are robustly predicted in the presence of unobservable phenomena. We describe in detail the mapping method that combines the merits of unsupervised manifold learning techniques and of mixtures of regressions. We validate our method with three publicly available data sets and we thoroughly benchmark four variants of the proposed algorithm with several state-of-the-art head-pose estimation methods.