激光与光电子学进展, 2019, 56 (13): 131003, 网络出版: 2019-07-11
多尺度卷积神经网络的头部姿态估计 下载: 1506次
Head Pose Estimation Based on Multi-Scale Convolutional Neural Network
图像处理 头部姿态估计 卷积神经网络 多尺度卷积 1×1卷积; imaging processing head pose estimation convolutional neural network multi-scale convolution 1×1 convolution;
摘要
针对多尺度卷积神经网络的头部姿态估计准确率在实际应用中易受到光照、遮挡等干扰因素的影响,以及大量运算导致算法运行速度较低的问题,提出了头部姿态估计算法。使用不同尺度的卷积核对输入的头部姿态图片进行特征提取,丰富了图像特征,同时保留了图像信息,增强了算法对干扰因素的稳健性。引入1×1卷积对网络结构参数进行降维,降低了系统的运算量,提高了算法的时效性。实验结果表明,所提算法在Pointing'04和CAS-PEAL-R1数据库上的识别率分别为96.5%和98.9%,对于光照、表情、遮挡等干扰表现出较好的稳健性,具有较快的运行速度。
Abstract
The accuracy of head pose estimation is easy to be affected by illumination, occlusion and other disturbances in practical applications and a large number of calculations are difficult to meet timeliness of practical applications. In order to solve these problems, a method based on multi-scale convolutional neural network is proposed. The feature extraction of the input head pose image is performed by using different scale convolution kernels, which enriches the image features while preserving the image information, and enhances the robustness of the algorithm to the interference factors. At the same time, the 1×1 convolution is introduced to reduce the network structure parameters, reduce the computational complexity of the system, and improve the timeliness of the algorithm. The result of experiment shows that the recognition rates of the proposed algorithm on Pointing'04 and CAS-PEAL-R1 databases are 96.5% and 98.9%, respectively. The method shows good robustness to illumination, expression, occlusion and other disturbances, and has better operation and speed.
梁令羽, 张天天, 何为. 多尺度卷积神经网络的头部姿态估计[J]. 激光与光电子学进展, 2019, 56(13): 131003. Lingyu Liang, Tiantian Zhang, Wei He. Head Pose Estimation Based on Multi-Scale Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(13): 131003.