文献类型：期刊文献

中文题名：基于非局部高分辨率网络的轻量化人体姿态估计方法

英文题名：Lightweight human pose estimation method based on non-local high-resolution network

作者：孙琪翔[1];何宁[2];张敬尊[2];宏晨[1]

第一作者：孙琪翔

机构：[1]北京联合大学机器人学院,北京100101;[2]北京联合大学智慧城市学院,北京100101

第一机构：北京联合大学机器人学院

年份：2022

卷号：42

期号：5

起止页码：1398-1406

中文期刊名：计算机应用

外文期刊名：journal of Computer Applications

收录：CSTPCD;;北大核心:【北大核心2020】；CSCD:【CSCD_E2021_2022】；

基金：国家自然科学基金资助项目(61872042);国家重点研发计划项目(2018AAA0100804);北京市教委科技计划重点项目(KZ201911417048);北京市教委科技计划面上项目(KM202111417009);北京联合大学人才强校优选计划项目(BPHR2020AZ01,BPHR2020EZ01);北京联合大学研究生科研创新项目(YZ2020K001)。

语种：中文

中文关键词：人体姿态估计;非局部模块;轻量化;Ghost模块;高分辨率网络

外文关键词：human pose estimation;non-local module;lightweight;Ghost module;high-resolution network

摘要：人体姿态估计是计算机视觉中的基本任务之一,可应用于动作识别、游戏、动画制作等领域。当前深度网络模型的设计大多通过加深网络以获得更好的性能,结果导致计算资源的需求超出嵌入式设备和移动设备的计算能力,达不到实际应用要求。针对上述问题,提出了一种融合Ghost模块结构的轻量级网络模型,即使用Ghost模块替换原高分辨率网络中的基础模块,从而减少网络模型的参数量。此外,设计了非局部高分辨率网络,即在网络1/32分辨率阶段融合非局部网络模块,使网络具有获取全局特征的能力,从而提高人体姿态估计的准确率,并在保证模型准确率的前提下降低网络参数量。在MPII人体姿态估计数据集和COCO人体姿态估计数据集上的实验结果表明,所提网络模型与原高分辨率网络相比,在网络模型参数量降低40%的情况下,人体姿态估计准确率提升了1.8个百分点。
Human pose estimation is one of the basic tasks in computer vision,which can be applied to the fields such as action recognition,games,and animation production.The current designs of deep network model mostly use deepening the network to obtain better performance.As a result,the demand for computing resources is beyond the computing power of embedded devices and mobile devices,and the requirements of actual applications can not be met.In order to solve the problems,a new lightweight network model integrating Ghost module structure was proposed,that is,the Ghost module was used to replace the basic module in the original high-resolution network,thereby reducing the number of network parameters.In addition,a non-local high-resolution network was designed,that is,the non-local network module was fused in the 1/32 resolution stage of the network,so that the network has the ability to obtain global features,thereby improving the accuracy of human pose estimation,and reducing the network parameters while ensuring the accuracy of model.Experiments were carried out on the human pose estimation datasets such as Max Planck Institut Informatik(MPII)and the Common Objects in COntext(COCO).Experimental results indicate that,compared with the original high-resolution network,the proposed network model has the accuracy of human pose estimation increased by 1.8 percentage points with the number of network parameters reduced by 40%.