融入双注意力的高分辨率网络人体姿态估计

doi:10.19678/j.issn.1000-3428.0060493

计算机工程 ›› 2022, Vol. 48 ›› Issue (2): 314-320. doi: 10.19678/j.issn.1000-3428.0060493

• 开发研究与工程应用 • 上一篇

融入双注意力的高分辨率网络人体姿态估计

罗梦诗¹, 徐杨^1,2, 叶星鑫¹

1. 贵州大学大数据与信息工程学院, 贵阳 550025;
2. 贵阳铝镁设计研究院有限公司, 贵阳 550009

收稿日期:2021-01-05 修回日期:2021-02-25 发布日期:2021-02-26
作者简介:罗梦诗(1995-),女,硕士研究生,主研方向为计算机视觉、机器学习;徐杨(通信作者),副教授、博士;叶星鑫,硕士研究生。
基金资助:
贵州大学人才引进项目（2015-12）；贵州省科技计划项目（黔科合LH字［2016］7429号）。

Human Pose Estimation Using High Resolution Network with Dual Attention

LUO Mengshi¹, XU Yang^1,2, YE Xingxin¹

1. College of Big Data and Information Engineering, Guizhou University, Guiyang 550025, China;
2. Guiyang Aluminum-magnesium Design and Research Institute Co., Ltd., Guiyang 550009, China

Received:2021-01-05 Revised:2021-02-25 Published:2021-02-26

摘要/Abstract

摘要： 在人体姿态估计任务中，针对高分辨率网络提取和融合特征图的特征信息时不能有效获取多通道信息和空间特征信息，导致人体姿态估计结果不够精确。在高分辨率网络（HRNet）的基础上，提出一种融入双注意力的高分辨率人体姿态估计网络ENNet。通过引入通道注意力，构造E-ecaneck模块和E-ecablock模块作为基础模块，最大程度地对多通道提取足够多的有用信息，在每一阶段子网的多分辨率融合阶段融入空间注意力机制，提取并融合不同分辨率特征信息，通过上采样的方式输出所有融合低分辨率的高分辨率表征。在公开数据集MS COCO2017上进行验证和测试，结果表明，相比于高分辨率网络，该方法mAP提高3.4%，有效改善网络多分辨率表征的信息融合能力，明显提升基础高分辨率网络HRNet的估计精确度。

关键词: 人体姿态估计, 高分辨率网络, 多分辨率融合, 通道注意力, 空间注意力

Abstract: In the human body posture estimation tasks, high resolution networks often fail to obtain multi-channel information and spatial feature information when extracting and fusing the feature information of feature maps, which reduces the accuracy of body posture estimation.To address the problem, this paper proposes a high resolution network(ENNet) with dual attention for body pose estimation.Channel attention is introduced to construct the E-ecaneck module and E-ecablock module, which are used as basic modules to extract useful information from multiple channels to the greatest extent.Then in the multi-resolution fusion stage of each subnet, the spatial attention mechanism is integrated to extract and fuse the feature information of different resolutions.Finally, all high-resolution representations with low resolution are output by upsampling.The network is validated and tested on the public dataset MS COCO2017.Results show that compared with high-resolution networks, the proposed method increases mAP by 3.4%, and effectively improves the information fusion capability of multi-resolution representation of network.It also significantly improves the estimation accuracy of the basic high-resolution network, HRNet.

Key words: human pose estimation, high resolution network, multi-resolution fusion, channel attention, spatial attention

中图分类号:

TP391.4

罗梦诗, 徐杨, 叶星鑫. 融入双注意力的高分辨率网络人体姿态估计[J]. 计算机工程, 2022, 48(2): 314-320.

LUO Mengshi, XU Yang, YE Xingxin. Human Pose Estimation Using High Resolution Network with Dual Attention[J]. Computer Engineering, 2022, 48(2): 314-320.

http://www.ecice06.com/CN/Y2022/V48/I2/314

图/表 13

20220301182229

20220301182232

20220301182235

20220301182239

20220301182242

20220301182245

20220301182248

20220301182251

20220301182255

20220301182258

20220301182301

20220301182304

20220301182307

参考文献

[1] TIJANA V, ALEX D, LAURA H, et al.Systematic literature review of hand gestures used in human computer interaction interfaces[J].International Journal of Human-Computer Studies, 2019, 129:74-94.
[2] 张聪聪, 何宁, 孙琪翔, 等.基于注意力机制的3D DenseNet人体动作识别方法[J].计算机工程, 2021, 47(11):313-320. ZHANG C C, HE N, SUN Q X, et al.Human motion recognition method based on attention mechanism of 3D DenseNet[J].Computer Engineering, 2021, 47(11):313-320.(in Chinese)
[3] KREISS S, BERTONI L, ALAHI A.PifPaf:composite fields for human pose estimation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:11969-11978.
[4] FANG H S, XIE S, TAI Y W, et al.RMPE:regional multi-person pose estimation[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2353-2362.
[5] HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:770-778.
[6] CHU X, OUYANG W, LI H, et al.Structured feature learning for pose estimation[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:4715-4723.
[7] OUYANG W, MA C, YUILLE AL, et al.Multi-context attention for human pose estimation[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:5669-5678.
[8] TOSHEV A, SZEGEDY C.DeepPose:human pose estimation via deep neural networks[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2014:1653-1660.
[9] CARREIRA J, AGRAAL P, FRAGKIADAKI K, et al.Human pose estimation with iterative error feedback[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:4733-4742.
[10] NEWELL A, YANG K Y, DENG J.Stacked hourglass networks for human pose estimation[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:483-499.
[11] CHENG B, XIAO B, WANG J, et al.HigherHRNet:scale-aware representation learning for bottom-up human pose estimation[EB/OL].[2020-12-01].https://arxiv.org/abs/1908.10357.
[12] CHEN Y, WANG Z, PENG Y, et al.Cascaded pyramid network for multi-person pose estimation[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:7103-7112.
[13] SUN K, XIAO B, LIU D, et al.Deep high-resolution representation learning for human pose estimation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:5686-5696.
[14] WANG Q, WU B, ZHU P, et al.ECA-Net:efficient channel attention for deep convolutional neural networks[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle, USA:IEEE Press, 2020:11531-11539.
[15] HU J, SHEN L, SUN G.Squeeze-and-excitation networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:7132-7141.
[16] WANG X, GIRSHICK R, GUPTA A, et al.Non-local neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:7794-7803.
[17] YANG Z, ZHU L, WU Y, et al.Gated channel transformation for visual recognition[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:11794-11803.
[18] YANG Y, RAMANAN D.Articulated pose estimation with flexible mixtures-of-parts[C]//Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2011:1385-1392.
[19] XIAO B, WU H P, WEI Y C.Simple baselines for human pose estimation and tracking[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2018:466-481.
[20] CAO Z, HIDALGO G, SIMON T, et al.OpenPose:realtime multi-person 2D pose estimation using part affinity fields[EB/OL].[2020-12-01].https://arxiv.org/abs/1812.08008.
[21] LI J, WANG C, ZHU H, et al.CrowdPose:efficient crowded scenes pose estimation and a new benchmark[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:10855-10864.

选择文件类型/文献管理软件名称

选择包含的内容

融入双注意力的高分辨率网络人体姿态估计

Human Pose Estimation Using High Resolution Network with Dual Attention

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	卢昂, 储珺, 冷璐. 基于高低频特征增强的图像去雾[J]. 计算机工程, 2023, 49(8): 174-181.
[2]	刘豪, 吴红兰, 房宇轩. 结合全局上下文信息的高效人体姿态估计[J]. 计算机工程, 2023, 49(7): 102-109.
[3]	王款, 宣士斌, 何雪东, 李紫薇, 李嘉祥. 基于交叉注意力Transformer的人体姿态估计方法[J]. 计算机工程, 2023, 49(7): 223-231.
[4]	钟宝荣, 吴夏灵. 基于高分辨率网络的轻量型人体姿态估计研究[J]. 计算机工程, 2023, 49(4): 226-232,239.
[5]	邹国建, 赖子良, 李晔. 基于时空注意力网络的动态高速路网交通速度预测[J]. 计算机工程, 2023, 49(2): 303-313.
[6]	王帅坤, 周志勇, 胡冀苏, 钱旭升, 耿辰, 陈光强, 纪建松, 戴亚康. 基于深度学习的肝脏CT-MR图像无监督配准[J]. 计算机工程, 2023, 49(1): 223-233.
[7]	于敏, 屈丹, 司念文. 改进的RetinaNet目标检测算法[J]. 计算机工程, 2022, 48(8): 249-257.
[8]	白杰, 张赛, 李艳萍. 基于改进交错组卷积的眼底硬性渗出物自动分割[J]. 计算机工程, 2022, 48(7): 307-314.
[9]	史宝岱, 张秦, 李瑶, 李宇环. 面向图像目标识别的轻量化卷积神经网络[J]. 计算机工程, 2022, 48(6): 257-262.
[10]	张云帆, 易尧华, 汤梓伟, 王新宇. 基于通道注意力机制的文本生成图像方法[J]. 计算机工程, 2022, 48(4): 206-212,222.
[11]	武茜, 贾世杰. 基于多通道注意力机制的人脸替换鉴别[J]. 计算机工程, 2022, 48(2): 180-185,193.
[12]	宋佳, 陈程立诏. 基于多流网络一致性的视频显著性检测[J]. 计算机工程, 2022, 48(2): 215-223.
[13]	刘圣杰, 何宁, 于海港, 王程, 韩文静. 引入坐标注意力和自注意力的人体关键点检测研究[J]. 计算机工程, 2022, 48(12): 86-94.
[14]	王柳程, 欧阳城添, 梁文. 基于改进特征金字塔网络的人体姿态估计[J]. 计算机工程, 2021, 47(8): 251-259,270.
[15]	刘勇, 李杰, 张建林, 徐智勇, 魏宇星. 基于深度学习的二维人体姿态估计研究进展[J]. 计算机工程, 2021, 47(3): 1-16.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

融入双注意力的高分辨率网络人体姿态估计

Human Pose Estimation Using High Resolution Network with Dual Attention

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献

相关文章 15

编辑推荐

Metrics

本文评价