基于改进CPMs和SqueezeNet的轻量级人体骨骼关键点检测模型  

Lightweight human skeleton key point detection model based on improved convolutional pose machines and SqueezeNet

作　　者：强保华[1,2] 翟艺杰 陈金龙[1] 谢武[1] 郑虹[1] 王学文[2] 张世豪 QIANG Baohua;ZHAI Yijie;CHEN Jinlong;XIE Wu;ZHENG Hong;WANG Xuewen;ZHANG Shihao(Guangxi Key Laboratory of Trusted Software(Guilin University of Electronic Technology),Guilin Guangxi 541004,China;Guangxi Key Laboratory of Image and Graphics Intelligent Processing(Guilin University of Electronic Technology),Guilin Guangxi 541004,China)

机构地区：[1]广西可信软件重点实验室(桂林电子科技大学),广西桂林541004 [2]广西图像图形与智能处理重点实验室(桂林电子科技大学),广西桂林541004

出　　处：《计算机应用》2020年第6期1806-1811,共6页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61762025);广西重点研究发展计划项目(AB17195053,AB18126063);广西自然科学基金资助项目(2017GXNSFAA198226);桂林科技发展计划项目(20180107-4)。

摘　　要：针对目前的人体骨骼关键点检测模型参数多、训练时间长和检测速度慢的问题,提出了一种将人体骨骼关键点检测模型CPMs与小型卷积神经网络模型SqueezeNet相结合的检测方法。首先,采用4个Stage的CPMs(CPMsStage4)对人物图像进行关键点检测;然后,在CPMs-Stage4中引入SqueezeNet的Fire Module网络结构,利用Fire Module结构大大压缩模型参数,得到一种新的轻量级人体骨骼关键点检测模型SqueezeNet15-CPMs-Stage4。在扩展的LSP数据集上的验证结果显示,与CPMs相比,SqueezeNet15-CPMs-Stage4模型在训练时间上减少86.68%,在单张图像检测时间上减少44.27%,准确率达到90.4%;与改进的VGG-16、DeepCut和DeeperCut三种参照模型相比,SqueezeNet15-CPMs-Stage4模型在训练时间、检测速度和准确率方面均是最优的。实验结果表明,所提模型不仅检测准确率高,而且训练时间短、检测速度快,能够有效降低人体骨骼关键点检测模型的训练成本。In order to solve the problems of too many parameters,long training time and slow detection speed of the existing human skeleton key point detection models,a detection method combining the human skeleton key point detection model called Convolutional Pose Machines(CPMs)and the lightweight convolutional neural network model called SqueezeNet was proposed.Firstly,the CPMs with 4 stages(CPMs-Stage4)was used to detect the key points of the human images.Then,the Fire Module network structure of SqueezeNet was introduced into CPMs-Stage4 to reduce the model parameters greatly,and thus to obtain a new lightweight human skeleton key point detection model called SqueezeNet15-CPMs-Stage4.The verification results on the extended Leeds Sports Pose(LSP)dataset show that,compared with CPMs,SqueezeNet15-CPMs-Stage4 model has the training time reduced by 86.68%,the detection time of single image reduced by 44.27%,and the detection accuracy of 90.4%;and the proposed model performs the best in training time,detection speed and accuracy compared with three reference models improved VGG-16,DeepCut and DeeperCut.The experimental results show that the proposed model achieves high detection accuracy with short training time and fast detection speed,and can effectively reduce the training cost of the human skeleton key point detection model.

关 键 词：人体骨骼关键点检测 人体姿态估计 深度学习 卷积神经网络 轻量级 CPMS SqueezeNet 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]