Please wait a minute...
浙江大学学报(理学版)  2021, Vol. 48 Issue (5): 521-530    DOI: 10.3785/j.issn.1008-9497.2021.05.001
图像分析与三维重建     
基于单目摄像头的自主健身监测系统
余鹏, 刘兰, 蔡韵, 何煜, 张松海
清华大学 计算机科学与技术系,北京 100084
Home fitness monitoring system based on monocular camera
YU Peng, LIU Lan, CAI Yun, HE Yu, ZHANG Songhai
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
 全文: PDF(1685 KB)   HTML  
摘要: 随着在线健身资源的日益丰富,自主健身已成为新的运动趋势。然而由于缺少专业健身教练的动作指导与纠正,自主健身通常无法保障健身效果且容易造成运动损伤,因此需要对健身动作准确性进行实时监测。现有的健身监测设备往往依托大屏幕、深度摄像头或传感器等硬件,存在设备昂贵、安装不便、使用场景受限等问题,较难满足大众健身的需求。随着人体关键点检测技术的不断成熟,通过手机单目摄像头即可实现对人体姿态的识别,且有较高的准确度和速度,使得在手机端实现低成本、多场景的健身监测成为可能。基于以上背景,设计了三维场景下基于角度阈值的健身动作评估算法,依托于手机单目摄像头和3D人体关键点检测技术,实时检测用户健身动作是否标准并通过语音给出相应提示。同时,在安卓手机上实现了原型系统,通过一系列用户实验验证了系统的可用性与实时性,通过与近年相关工作的对比实验,验证了动作评估方法的准确性。结果表明,本文方法与系统被用户所认可,健身动作评估准确率较高、响应速度满足实时性要求。
关键词: 自主健身人体关键点检测动作监测虚拟健身教练    
Abstract: With the increasing richness of online fitness resources, autonomous fitness has become a new sporting trend. However, due to the lack of action guidance and correction by professional fitness coaches, autonomous fitness usually cannot guarantee the fitness effect and is easy to cause sports injuries, so real-time monitoring of fitness actions is required. Existing fitness monitoring equipment usually relies on professional hardware such as big screens, stereo camera and other sensors. As a result, they fail to satisfy common needs for virtual fitness due to high cost, complexity of installation and limited application scenario. With gradual maturing of human pose estimation technique, identification of human face and movements of limbs can be realized through easily accessible cell phone camera with high accuracy and speed. Low cost, multi-scenario virtual fitness monitoring on mobile terminal thus it made possible. Based on the background above, this work designs a fitness action evaluation algorithm based on angle thresholds in 3D scenes which relies on cell phone monocular camera and 3D human key point detection technology. The algorithm can detect whether the user's fitness actions are standard in real time and give corresponding responses through voice. The work has implemented a prototype system on an Android phone. This work verifies the usability and real-time performance of the algorithm and the system through a series of user experiments. It also verifies the accuracy of the action evaluation algorithm through comparative experiments with relevant work in recent years. Results shows that the algorithm and functions of the prototype system were greatly recognized by the users with high accuracy, reasonable responding speed for real time usage.
Key words: autonomous fitness    virtual personal trainer    human pose estimation    exercise monitoring
收稿日期: 2020-12-09 出版日期: 2021-09-15
CLC:  TP 391.41  
基金资助: 国家自然科学基金资助项目(61772298,61832016);可视媒体智能处理与内容安全北京市高等学校工程研究中心项目;清华-腾讯互联网创新技术联合实验室项目.
通讯作者: ORCID:https://orcid.org/0000-0002-0357-681X,E-mail:hooyeeevan2511@gmail.com.     E-mail: hooyeeevan2511@gmail.com
作者简介: 余鹏(1997—),ORCID:https://orcid.org/0000-001-6286-0186,男,硕士,主要从事图像/视频处理研究,E-mail:anicca97@163.co;
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
余鹏
刘兰
蔡韵
何煜
张松海

引用本文:

余鹏, 刘兰, 蔡韵, 何煜, 张松海. 基于单目摄像头的自主健身监测系统[J]. 浙江大学学报(理学版), 2021, 48(5): 521-530.

YU Peng, LIU Lan, CAI Yun, HE Yu, ZHANG Songhai. Home fitness monitoring system based on monocular camera. Journal of Zhejiang University (Science Edition), 2021, 48(5): 521-530.

链接本文:

https://www.zjujournals.com/sci/CN/10.3785/j.issn.1008-9497.2021.05.001        https://www.zjujournals.com/sci/CN/Y2021/V48/I5/521

1 刁在箴,马更娣,张莹,等.中国体育健身俱乐部发展概况之研究[J].北京体育大学学报,2002(6):744-745,750. DOI: 10.3969/j.issn.1007-3612.2002. 06.009 DIAO Z Z, MA G D, ZHANG Y, et al. Research on general situation of clubs for body-building in China[J]. Journal of Beijing University of Physical Education, 2002(6):744-745,750. DOI: 10.3969/j.issn.1007-3612.2002.06.009
2 XIA S H, GAO L, LAI Y K, et al. A survey on human performance capture and animation[J]. Journal of Computer Science and Technology, 2017, 32: 536-554. DOI: 10.1007/s11390-017-1742-y
3 VELLOSO E, BULLING A, GELLERSEN H, et al. Qualitative activity recognition of weight lifting exercises[C]//Proceedings of 4th Augmented Human International Conference. New York: Association for Computing Machinery, 2013: 116-123. DOI: 10.1145/2459236.2459256
4 CHANG K H, CHEN M Y, CANNY J. Tracking free-weight exercises[C]//Proceedings of the 9th International Conference on Ubiquitous Computing. Berlin/Heidelberg: Springer-Verlag, 2007: 19-37. DOI: 10.5555/1771592.1771594
5 CREMA C, DEPARI A, FLAMMINI A, et al. IMU-based solution for automatic detection and classification of exercises in the fitness scenario[C]//2017 IEEE Sensors Applications Symposium (SAS). Piscataway: IEEE, 2017: 1-6. DOI: 10. 1109/SAS.2017.7894068
6 DING H, SHANGGUAN L F, YANG Z, et al. FEMO: A platform for free-weight exercise monitoring with RFIDS[C]//Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems. New York: Association for Computing Machinery, 2015: 141-154. DOI: 10.1145/2809695. 2809708
7 ZHOU B, SUNDHOLM M, CHENG J Y, et al. Never skip leg day: A novel wearable approach to monitoring gym leg exercises[C]//2016 IEEE International Conference on Pervasive Computing and Communications. Piscataway: IEEE, 2016: 1-9. DOI: 10.1109/PERCOM.2016. 7456520
8 HAO T, XING G L, ZHOU G. RunBuddy: A smartphone system for running rhythm monitoring[C]// Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York: Association for Computing Machinery, 2015: 133-144. DOI: 10.1145/2750858. 2804293
9 JIN X, YAO Y, JIANG Q L, et al. Virtual personal trainer via the Kinect sensor[C]//2015 IEEE 16th International Conference on Communication Technology (ICCT). Piscataway: IEEE, 2015: 460-463. DOI:10.1109/icct.2015.7399879
10 KUMAR P, SAINI R, YADAVA M, et al. Virtual trainer with real-time feedback using kinect sensor[C]//2017 IEEE Region 10 Symposium (TENSYMP). Piscataway: IEEE, 2017: 1-5. DOI: 10.1109/TENCONSpring.2017.8070063
11 QIAO S, WANG Y L, LI J. Real-time human gesture grading based on OpenPose[C]//2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). Piscataway: IEEE, 2017: 1-6. DOI: 10.1109/CISP-BMEI.2017.8301910
12 DEB S, SHARAN A, CHATURVEDI S, et al. Interactive dance lessons through human body pose estimation and skeletal topographies matching[J]. International Journal of Computational Intelligence & IoT, 2018, 2(4):711-716.
13 WEI S E, RAMAKRISHNA V, KANADE T, et al. Convolutional pose machines[C]//2016 IEEE conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 4724-4732. DOI: 10.1109/CVPR.2016.511.
14 NEWELL A, YANG K Y, DENG J. Stacked hourglass networks for human pose estimation[C]// European Conference on Computer Vision (ECCV). Cham: Springer, 2016: 483-499. DOI: 10.1007/978-3-319-46484-8_29
15 HE K, GKIOXARI G, DOLLÁR P, et al. Mask RCNN[C]// 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2961-2969. DOI: 10.1109/tpami.2018.2844175
16 CHEN Y L, WANG Z C, PENG Y X, et al. Cascaded pyramid network for multi-person pose estimation[C]// 2018 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7103-7112. DOI: 10.1109/CVPR.2018.00742.
17 LI W B, WANG Z C, YIN B Y, et al. Rethinking on multi-stage networks for human pose estimation[Z/OL]. (2019-01-01).https://arXiv.org/abs/1901. 00148. doi:10.1609/aaai.v34i07.6797
18 FANG H S, XIE S Q, TAI Y W, et al. RMPE: Regional multi-person pose estimation[C]// 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2353-2362. DOI: 10.1109/ICCV.2017.256.
19 SUN K, XIAO B, LIU D, et al. Deep high-resolution representation learning for human pose estimation[C]//2019 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 5686-5696. DOI: 10.1109/CVPR.2019.00584.
20 CAO Z, SIMON T, WEI S E, et al. Realtime multi-person 2D pose estimation using part affinity fields[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2017: 1302-1310. DOI: 10.1109/CVPR. 2017.143.
21 NEWELL A, HUANG Z, DENG J. Associative embedding: End-to-end learning for joint detection and grouping[C]// 31st International Conference on Neural Information Processing Systems. New York: Curran Associates Inc,2017: 2274-2284.
22 XIA F T, WANG P, CHEN X J, et al. Joint multi-person pose estimation and semantic part segmentation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2017: 6780-6789. DOI: 10.1109/CVPR. 2017.644.
23 SHOTTON J, FITZGIBBON A, COOK M, et al. Real-time human pose recognition in parts from single depth images[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2011: 1297-1304. DOI: 10.1109/CVPR.2011.5995316.
24 HAQUE A, PENG B Y, LUO Z L, et al. Towards viewpoint invariant 3D human pose estimation[C]//European Conference on Computer Vision. Cham: Springer, 2016: 160-177. DOI: 10.1007/978-3-319-46448-0_10
25 CHEN C H, RAMANAN D. 3D human pose estimation = 2D pose estimation + matching[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2017: 5759-5767. DOI: 10.1109/CVPR.2017.610.
26 MARTINEZ J, HOSSAIN R, ROMERO J, et al. A simple yet effective baseline for 3D human pose estimation[C]// 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway: IEEE, 2017: 2659-2668. DOI: 10.1109/ICCV.2017.288.
27 GÜLER R A,NEVEROVA N,KDKKINOS I.DensePose:Dense human pose estimation in the wild[C]//IEEE/CVF Corference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:7297-7306. doi:10.1109/cvpr.2018.00762
28 PAVLLO D, FEICHTENHOFER C, GRANGIER D, et al. 3D human pose estimation in video with temporal convolutions and semi-supervised training[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2019: 7745-7754. DOI: 10.1109/CVPR.2019.00794
29 IONESCU C, PAPAVA D, OLARU V, et al. Human 3.6m: Large scale datasets and predictive methods for 3D human sensing in natural environments[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 36(7): 1325-1339. DOI: 10.1109/TPAMI.2013.248
[1] 方于华,叶枫. MFDC-Net:一种融合多尺度特征和注意力机制的乳腺癌病理图像分类算法[J]. 浙江大学学报(理学版), 2023, 50(4): 455-464.
[2] 虞瑞麒,刘玉华,沈禧龙,翟如钰,张翔,周志光. 表征学习驱动的多重网络图采样[J]. 浙江大学学报(理学版), 2022, 49(3): 271-279.
[3] 祝锦泰,叶继华,郭凤,江蕗,江爱文. FSAGN: 一种自主选择关键帧的表情识别方法[J]. 浙江大学学报(理学版), 2022, 49(2): 141-150.
[4] 钟颖,王松,吴浩,程泽鹏,李学俊. 基于SEMMA的网络安全事件可视探索[J]. 浙江大学学报(理学版), 2022, 49(2): 131-140.
[5] 朱强,王超毅,张吉庆,尹宝才,魏小鹏,杨鑫. 基于事件相机的无人机目标跟踪算法[J]. 浙江大学学报(理学版), 2022, 49(1): 10-18.
[6] 杨猛,丁曙,马云涛,谢佳翊,段瑞枫. 基于纹理特征的小麦锈病动态模拟方法[J]. 浙江大学学报(理学版), 2022, 49(1): 1-9.
[7] 傅汝佳, 冼楚华, 李桂清, 万隽杰, 曹铖, 杨存义, 高月芳. 面向表型精确鉴定的豆株快速三维重建[J]. 浙江大学学报(理学版), 2021, 48(5): 531-539.
[8] 桂志强, 姚裕友, 张高峰, 徐本柱, 郑利平. 3D-power图的快速生成方法[J]. 浙江大学学报(理学版), 2021, 48(4): 410-417.
[9] 徐敏, 王科, 戴浩然, 罗晓博, 余炜伦, 陶煜波, 林海. 基于电子病历的乳腺癌群组与治疗方案可视分析[J]. 浙江大学学报(理学版), 2021, 48(4): 391-401.
[10] 邹北骥, 杨文君, 刘姝, 姜灵子. 面向自然场景图像的三阶段文字识别框架[J]. 浙江大学学报(理学版), 2021, 48(1): 1-8.
[11] 陈园琼, 邹北骥, 张美华, 廖望旻, 黄嘉儿, 朱承璋. 医学影像处理的深度学习可解释性研究进展[J]. 浙江大学学报(理学版), 2021, 48(1): 18-29.
[12] 邓惠俊. 排序支持的交互数据分类算法及其应用[J]. 浙江大学学报(理学版), 2021, 48(1): 9-17.
[13] 李华飙, 侯小刚, 王婷婷, 赵海英. 基于规则学习的传统纹样统一生成模式研究[J]. 浙江大学学报(理学版), 2020, 47(6): 669-676.
[14] 檀结庆, 曹宁宁. 一种四边形网格上的Midedge细分格式[J]. 浙江大学学报(理学版), 2019, 46(2): 154-163.