基于Huber指数平方损失函数的二维人体姿态估计网络

马 金 伯 

基于Huber指数平方损失函数的二维人体姿态估计网络

引用本文：马金伯 .基于Huber指数平方损失函数的二维人体姿态估计网络[J].计算技术与自动化,2021,(3):152-156

摘要点击次数: 459

全文下载次数: 0

作者	单位
马金伯 	(东北大学理学院, 辽宁，沈阳 110819)

中文摘要:人体姿态估计是计算机视觉领域的一个研究热点，已经应用于教育、体育等方面，在视频监控、人机交互、智能校园等领域有着广阔的应用前景。简单的姿态估计基线方法在沙漏残差模块中加入几层反卷积层，使用均方误差（MSE）损失函数，结构和算法复杂度较低且能够较为精确地预测出关节点热图。首先，采用分段函数H-ESL（huber-exponential squared loss）损失函数，克服了MSE损失函数对于异常值较为敏感的缺点。其次，提出的网络在基线方法的网络上加入了注意力机制，并将大的卷积核转换成小的卷积核，使得网络精度提升的同时减少参数量及计算量，从而提高网络的预测效率。拟建网络利用COCO2017数据集的地面真实值分别进行训练和验证，均实现了高精度，mAP提高了2.6％，证明该方法适用于各种人类关键热图的输入，并能取得良好的效果。

中文关键词:深度学习人体姿态估计损失函数热图 COCO数据集

A Two-dimensional Human Pose Estimation Network Based on Huber Exponential Square Loss Function

Abstract:As a hot topic in computer vision,human pose estimation has gradually penetrated into all aspects of education, sports and so on. It has a wide application prospect in the fields of video surveillance, human-computer interaction and intelligent campus.In the simple baseline method, several layers of deconvolution were added into the hourglass residual module, and the mean square error loss function is used.First, piecewise function H-ESL (Huber-Exponential Squared Loss) loss function is adopted to overcome the shortcoming that MSE loss function is sensitive to outliers.Secondly, the proposed network adds an attention mechanism to the network of the baseline method, and converts large convolution kernels into small convolution kernels, which improves the accuracy of the network and reduces the number of parameters and the amount of computation, thus improving the prediction efficiency of the network.The proposed network is trained and verified by ground truth value of COCO2017 dataset, and both of them achieve high precision. Map is increased by 2.6%, which proves that this method is suitable for heat mAP input of multiple human body key points and can achieve good results.

keywords:deep learning human pose estimation loss function heat map COCO datasets

查看全文 查看/发表评论 下载pdf阅读器