不同视角三维人体关键点动作相似度计算

doi:10.3969/j.issn.1006-2475.2025.07.009

摘要/Abstract

摘要： 摘要：目前线上健身、舞蹈教学视频资源丰富，但学员在学习过程中为比较与教学的动作自行拍摄的视频无法保证与教学的视角一致，会有角度和尺度的差异，不便于比较动作相似度。针对此问题，本文利用现有的三维人体姿态估计技术，提出一种可以用于不同视角下的单目摄像头拍摄的视频的动作相似度评估算法。对于2个不同视角的人物动作视频，首先用YOLOv8pose网络提取二维人体关键点，然后用GraphMLP网络升维成三维关键点。基于2组三维关键点序列计算欧氏距离矩阵，用DTW算法找出2组动作的对应帧，将对应帧的三维关键点通过旋转、放缩等手段调整视角，将不同视角的动作序列调整到同一方向，最后采用骨骼向量的余弦相似度作为相似度评判指标。利用不同视角的动作捕捉动画进行实验，验证了本文方法的有效性。

关键词: 关键词：YOLOv8pose, GraphMLP, 人体姿态估计, DTW, 余弦相似度, 不同视角

Abstract:
Abstract: With the abundance of online fitness and dance instructional videos， students often face difficulties in comparing their movements with those of the instructors due to inconsistencies in angles and scales when filming themselves， which hinders accurate movement similarity comparison. To fix this problem， this paper leverages existing 3D human pose estimation methods and proposes a motion similarity evaluation algorithm for videos filmed from different angles with a monocular camera. For two videos of human actions from different perspectives， this paper first extracts 2D human key points using the YOLOv8pose network， then elevates these to 3D key points using the GraphMLP network. This paper calculates the Euclidean distance matrix based on the two sets of 3D key point sequences and uses the DTW algorithm to identify corresponding frames between the two sets of actions. By adjusting the perspective of corresponding frames’3D key points through rotation and scaling， this paper aligns action sequences from different perspectives. Finally， the cosine similarity of skeletal vectors is used as the similarity evaluation metric. Experiments using mocap animations from different perspectives was conducted， the results demonstrated the effectiveness of the method proposed in this paper.

Key words: Key words: YOLOv8pose, GraphMLP, human pose estimation, dynamic time warping, cosine similarity, different perspectives

中图分类号:

中图分类号：TP391

李子贺, 王一丁. 不同视角三维人体关键点动作相似度计算[J]. 计算机与现代化, 2025, 0(07): 63-68.

LI Zihe, WANG Yiding. 3D Human Motion Similarity Estimation from Different Perspectives [J]. Computer and Modernization, 2025, 0(07): 63-68.

参考文献

［1］张亮亮. 多媒体技术在网球教学中的应用研究［J］. 文体用品与科技， 2018（16）:96-98.
［2］孙建秋. 巧用多媒体提高学生广播操的质量［J］. 青少年体育， 2014（9）:57-58.
［3］周升儒，陈志刚，邓伊琴. 基于PoseC3D的网球动作识别及评价方法［J］. 计算机工程与科学， 2023，45（1）:95-103.
［4］苏波，柴自强，王莉，等. 基于姿态估计的八段锦序列动作识别与评估［J］. 电子科学， 2022，35（12）84-90.
［5］王云鹏，吕诗雨，司海平，等. 基于人体骨架的国标舞蹈动作相似度计算研究［J］. 电子设计工程， 2023，31（11）:10-15.
［6］贾亚光，刘静，雷森，等. 基于Alphapose的跑步动作标准化评估［J］. 计算机时代， 2023（8）:117-120.
［7］辛义忠，邢志飞. 基于Kinect的人体动作识别方法［J］. 计算机工程与设计， 2016，37（4）:1056-1061.
［8］于景华，王庆，陈洪. 基于动作评价算法的体感舞蹈交互系统［J］. 计算机与现代化， 2018（6）:64-71.
［9］蔡兴泉，霍宇晴，李发建，等. 面向太极拳学习的人体姿态估计及相似度计算［J］. 图学学报， 2022，43（4）:695-706.
［10］ DANG Q， YIN J Q， WANG B， et al. Deep learning based 2D human pose estimation: A survey［J］. Tsinghua Science and Technology， 2019，24（6）:663-676.
［11］ ZHENG C， WU W H， CHEN C， et al. Deep learning-based human pose estimation: A survey［J］. ACM Computing Surveys， 2023，56（1）:Article No. 11.
［12］ LI S J， ZHANG W C， CHAN A B. Maximum-margin structured learning with deep networks for 3D human pose estimation［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision. IEEE， 2015:2848-2856.
［13］ PAVLAKOS G， ZHOU X W， DANIILIDIS K. Ordinal depth supervision for 3D human pose estimation［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2018:7307-7316.
［14］ PAVLAKOS G， ZHOU X W， DERPANIS K G， et al. Coarse-to-fine volumetric prediction for single-image 3D human pose［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2017:7025-7034.
［15］ CAO Z， SIMON T， WEI S E， et al. Realtime multi-person 2D pose estimation using part affinity fields［C］// Proceedings of the 2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2017:7291-7299.
［16］ SUN K， XIAO B， LIU D， et al. Deep high-resolution representation learning for human pose estimation［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2019: 5686-5696.
［17］ NEWELL A， YANG K Y， DENG J. Stacked hourglass networks for human pose estimation［C］// Proceedings of the 2016 14th European Conference on Computer Vision. Springer， 2016:483-499.
［18］ CHEN Y L， WANG Z C， PENG Y X， et al. Cascaded pyramid network for multi-person pose estimation［C］// Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2018:7103-7112.
［19］ WEI S E， RAMAKRISHNA V， KANADE T， et al. Convolutional pose machines［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2016:4724-4732.
［20］ WANG J， LONG X， GAO Y， et al. Graph-PCNN: Two stage human pose estimation with graph pose refinement［C］// Proceedings of the 2020 16th European Conference on Computer Vision. Springer， 2020:492-508.
［21］ MARTINEZ J， HOSSAIN R， ROMERO J， et al. A simple yet effective baseline for 3D human pose estimation［C］// Proceedings of the IEEE International Conference on Computer Vision. IEEE， 2017:2640-2649.
［22］ PAVLLO D， FEICHTENHOFER C， GRANGIER D， et al. 3D human pose estimation in video with temporal convolutions and semi-supervised training［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. IEEE， 2019:7753-7762.
［23］ ZHENG C， ZHU S J， MENDIETA M， et al. 3D human pose estimation with spatial and temporal Transformers［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. IEEE， 2021:11636-11645.
［24］ LI W H， LIU M Y， LIU H， et al. GraphMLP: A graph MLP-like architecture for 3D human pose estimation［J］. arXiv preprint arXiv:2206.06420， 2022.
［25］ IONESCU C， PAPAVA D， OLARU V， et al. Human3. 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.
［26］ ANDRILUKA M， PISHCHULIN L， GEHLER P， et al. 2D human pose estimation: New benchmark and state of the art analysis［C］// Proceedings of the IEEE Conference on computer Vision and Pattern Recognition. IEEE， 2014: 3686-3693.
［27］ MAJI D， NAGORI S， MATHEW M， et al. YOLO-pose: Enhancing YOLO for multi person pose estimation using object keypoint similarity loss［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2022:3686-3693.

[1]	田丰, 邓晓平, 张桂青, 王保义. 基于改进kNN算法与暂稳态特征的非侵入式负荷监测方法[J]. 计算机与现代化, 2022, 0(10): 29-35.
[2]	周昆阳, 赵梦婷, 张海潮, 邵叶秦. 基于通道切分的人体姿态估计算法[J]. 计算机与现代化, 2021, 0(12): 27-36.
[3]	李一野1，2，邓浩江1，2. 基于改进余弦相似度的协同过滤推荐算法[J]. 计算机与现代化, 2020, 0(01): 69-.
[4]	谢浩然1，卫巍2，杨志辉3，邓居智1，葛坤朋1. 基于TF-IDF的新型广播电视节目协同推荐流程[J]. 计算机与现代化, 2019, 0(09): 65-.
[5]	杨雨诗,何博侠,周鑫，刘慧丽，葛方丽. 基于词库匹配的网络文本分类及预测[J]. 计算机与现代化, 2017, 0(10): 72-75.
[6]	印世乐，曾志勇. 一种改进的Nystrom谱聚类图像分割算法[J]. 计算机与现代化, 2014, 0(4): 20-23.
[7]	茅剑;林奇. 基于声纹识别的嵌入式防盗系统[J]. 计算机与现代化, 2009, 1(11): 163-165.