Department of Computer Engineering, Keimyung University, Daegu 42601, Korea.
Sensors (Basel). 2019 Mar 6;19(5):1147. doi: 10.3390/s19051147.
Semi-supervised learning is known to achieve better generalisation than a model learned solely from labelled data. Therefore, we propose a new method for estimating a pedestrian pose orientation using a soft-target method, which is a type of semi-supervised learning method. Because a convolutional neural network (CNN) based pose orientation estimation requires large numbers of parameters and operations, we apply the teacher⁻student algorithm to generate a compressed student model with high accuracy and compactness resembling that of the teacher model by combining a deep network with a random forest. After the teacher model is generated using hard target data, the softened outputs (soft-target data) of the teacher model are used for training the student model. Moreover, the orientation of the pedestrian has specific shape patterns, and a wavelet transform is applied to the input image as a pre-processing step owing to its good spatial frequency localisation property and the ability to preserve both the spatial information and gradient information of an image. For a benchmark dataset considering real driving situations based on a single camera, we used the TUD and KITTI datasets. We applied the proposed algorithm to various driving images in the datasets, and the results indicate that its classification performance with regard to the pose orientation is better than that of other state-of-the-art methods based on a CNN. In addition, the computational speed of the proposed student model is faster than that of other deep CNNs owing to the shorter model structure with a smaller number of parameters.
半监督学习被认为比仅从标记数据中学习的模型具有更好的泛化能力。因此，我们提出了一种使用软目标方法估计行人姿态方向的新方法，软目标方法是一种半监督学习方法。由于基于卷积神经网络（CNN）的姿态方向估计需要大量的参数和操作，我们应用教师⁻学生算法通过将深度网络与随机森林相结合来生成具有高精度和紧凑性的压缩学生模型，其精度和紧凑性类似于教师模型。在使用硬目标数据生成教师模型之后，使用教师模型的软化输出（软目标数据）来训练学生模型。此外，行人的姿态具有特定的形状模式，并且由于其良好的空间频率定位特性以及能够保留图像的空间信息和梯度信息，因此将小波变换应用于输入图像作为预处理步骤。对于基于单目相机的考虑真实驾驶情况的基准数据集，我们使用了 TUD 和 KITTI 数据集。我们将所提出的算法应用于数据集的各种驾驶图像，结果表明，其关于姿态方向的分类性能优于其他基于 CNN 的最先进方法。此外，由于模型结构较短且参数较少，因此所提出的学生模型的计算速度比其他深度 CNN 更快。
