Mechanical Engineering Science

Computer Vision-Based Human Body Posture Correction System

QIUYangsen (School of Information science and Technology, Shijiazhuang Tiedao University), WANGYukun (School of Information science and Technology, Shijiazhuang Tiedao University), WUYuchen (School of Information science and Technology, Shijiazhuang Tiedao University), QIANGXinyi (School of Information science and Technology, Shijiazhuang Tiedao University), ZHANGYunzuo (School of Information science and Technology, Shijiazhuang Tiedao University)

Abstract


With the development of technology and the progress of life, more and more people, regardless of entertainment, learning, or work, cannot do without computer desks and cannot put down their mobile phones. Due to prolonged sitting and often neglecting the importance of posture, incorrect posture can often lead to health problems such as hunchback, lumbar muscle strain, and shoulder and neck pain over time. To address this issue, we designed a computer vision-based human body posture detection system. The system utilizes YOLOv8 technology to accurately locate key points of the human body skeleton, and then analyzes the coordinate positions and depth information of these key points to establish a criterion for distinguishing different postures. With the assistance of an SVM classifier, the system achieves an average recognition rate of 95%. Finally, we successfully deployed the posture detection system on Raspberry Pi hardware and conducted extensive testing. The test results demonstrate that the system can effectively detect various postures and provide real-time reminders to users to correct poor posture, demonstrating good practicality and stability.

Keywords


computer vision; human posture; deep learning; image processing

Full Text:

PDF

References


Moreira Rayele, et al. A computer vision-based mobile tool for assessing human posture: A validation study[J]. Computer Methods and Programs in Biomedicine, 2022 (214):106565.

Debnath B, O’Brien M, Yamaguchi M, et al. A review of computer vision-based approaches for physical rehabilitation and assessment[J]. Multimedia Systems, 2022,28(1):209-239.

Hellsten T, Karlsson J, Shamsuzzaman M, et al. The potential of computer vision-based marker-less human motion analysis for rehabilitation[J]. Rehabilitation Process and Outcome, 2021(10):1-12.

Andriluka M, Iqbal U, Insafutdinov E, et al. PoseTrack: A benchmark for human pose estimation and tracking[C]. Salt Lake City: IEEE, 2018.

Sun Ke. Hierarchical occlusion reasoning for human pose estimation with incomplete data[J]. IEEE Computer Vision and Pattern Recognition (CVPR), 2021(11):55-59.

Gao Y, Ren Y, Zhang D, et al. Multi-level attention network for fine-grained action recognition[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

Zhao Y, Xiong Y, Wang L, et al. Weakly supervised action recognition through contrastive spatiotemporal regions[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

Zhang Y, Cui W, Cao Y, et al. Multimodality human action recognition with deep attention mechanism[J]. Computers & Electrical Engineering, 2020(80):221-239.

Tang Y, Liu R. Skeleton Embedding of multiple granularity attention network for human action recognition[C]. International Conference on Articulated Motion and Deformable Objects Springer, 2020.

Liang ZJ, Wang XL, Huang R, et al. An Expressive deep model for human action parsing from a single image[C]. 2014 IEEE International Conference on Multimedia and Expo (ICME). Chengdu: IEEE, 2014.

Zhai W, Zhang Y, Cheng H, et al. Cooperative eye tracking: a gaze-aware interface for 3D object manipulation[C]. Proceedings of the ACM International Conference on Interactive Surfaces and Spaces, 2019.

Yang X, Chen Y, Liu J, et al. Rapid prototyping of tangible augmented reality interfaces: towards exploratory learning for science education[J]. Interactive Learning Environments, 2019,27(4):469-483.

Zhang D, Peng Y, Yang W, et al. Multi-viewpoint interaction with social robots: a case study of speech therapy for children with autism[J]. Journal of Intelligent & Robotic Systems, 2018,92(3-4):359-372.

Zhang R, Li J, Xiao T, et al. BodyPoseNet: Body pose estimation driven by deep neural networks[J]. Signal Processing: Image Communication, 2021(99):116290.

Chen L, Papandreou G, Kokkinos I, et al. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018,40(4):834-848.

Zeng W, Gao Y, Zheng Y, et al. DenseReg: Fully convolutional dense regression for accurate 3D human pose estimation[J]. IEEE Transactions on Image Processing, 2021(30):2830-2842.

Li J, Chen L, Wei Y, et al. CrowdPose: Efficient crowded scenes pose estimation and a new benchmark[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

Du W, Wang X, Wang X, et al. PoseFix: Model-agnostic general human pose refinement network[C]. Proceedings of the ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques, 2020.

Zhu L, Zhou C, Li S, et al. CTSegNet: A context-transformed segmentation network for brain tumor segmentation[C]. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine, 2019.

Ji Xiaodong, Yang Qiaoning, Yang Xiuhui, et al. Human pose estimation: multi-stage network based on HRNet [J]. Journal of Physics: Conference Series, 2022,(1):2400.

He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015,37(9):1904-1916.

Papandreou G, Zhu T, Kanazawa N, et al. Towards accurate multi-person pose estimation in the wild[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

Wei L, Zhang S, Dai J, et al. ST-GCN: Spatial temporal graph convolutional networks for skeleton-based action recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

Sun M, He X, Yang S. U^2-Net (RE) for Human Pose Estimation[J]. arXiv preprint arXiv, 2021(2102):380.

Zhou F, Zhu M, Bai J, et al. Deformable ConvNets v2: More deformable, better results[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

Carreira J, Agrawal P, Fragkiadaki K, et al. Associative embedding: End-to-end learning for joint detection and grouping[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.

Papandreou G, Zhu T, Kanazawa N, et al. PersonLab: Person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model[C]. Proceedings of the European Conference on Computer Vision, 2018.

Kreiss S, Bertoni A, Alahi A. PifPaf: Composite fields for human pose estimation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019.

Insafutdinov M, Pishchulin L, Andres B, et al. DeepCut: Joint subset partition and labeling for multi person pose estimation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.

Newell A, Yang K, Deng J. Stacked hourglass networks for human pose estimation[C]. Proceedings of the European Conference on Computer Vision (ECCV), 2016.

Chen Y, Wang Z, Peng Y, et al. Cascaded pyramid network for multi-person pose estimation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

Sun K, Xiao B, Liu D, et al. Deep high-resolution representation learning for human pose estimation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

Xiao B, Wu H, Wei Y. Simple baseline for human pose estimation and tracking[C]. Proceedings of the European Conference on Computer Vision (ECCV), 2018.

Wei L, Zhang S, Yin W, et al. Convolutional pose machines[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.




DOI: https://doi.org/10.33142/mes.v6i1.13221

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Yangsen QIU, Yukun WANG, Yuchen WU, Xinyi QIANG, Yunzuo ZHANG

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.