Abstract
Significance of human action recognition has increased manifolds due to its wide-scale application in the field of public security, gaming, etc., due to the introduction of various new technologies. We propose a framework that detects human action under different conditions and viewing angles that enable the identification of divergent patterns based on different spatiotemporal trajectories. In this paper, we use new technology such as MediaPipe Holistic which provides pose, face, and hand landmark detection models which parses the frames obtained through real-time device feed using OpenCV through our MediaPipe Holistic model and provide a total of 501 landmarks which is exported as coordinates to a CSV file upon which we train a custom multi-class classification model to understand the relationship between the class and coordinates to classify and detect custom body language pose. The machine learning classification algorithms implemented in this paper are random forest, linear regression, ridge classifier, and gradient boosting classifier.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
C. Lugaresi, J. Tang, H. Nash, C. McClanahan, E. Uboweja, M. Hays, F. Zhang, C.-L. Chang, M. Yong, J. Lee, W.-T. Chang, W. Hua, M. Georg, M. Grundmann (2019) MediaPipe: a framework for building perception pipelines
M. Sun, P. Kohli, J. Shotton, Conditional regression forests for human pose estimation, in Proceeding/CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012), pp. 3394–3401. https://doi.org/10.1109/CVPR.2012.6248079
A. Gupta, A. Kembhavi, L.S. Davis, Observing human-object interactions: using spatial and functional compatibility for recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(10), 1775–1789. https://doi.org/10.1109/TPAMI.2009.83
L. Liu, L. Shao, X. Li, K. Lu, Learning spatio-temporal representations for action recognition: a genetic programming approach. IEEE Trans. Cybernet. 46(1), 158–170 (2016). https://doi.org/10.1109/TCYB.2015.2399172
D. Ramanan, D. Forsyth (2004) Automatic annotation of everyday movements
W. Niu, J. Long, D. Han, Y. Wang, Human activity detection and recognition for video surveillance 1, 719–722 (2004). https://doi.org/10.1109/ICME.2004.1394293
I. Grishchenko, V. Bazarevsky, MediaPipe holistic—simultaneous face, hand and pose prediction, on device. Google AI Blog, Google, 10 Dec 2020. https://ai.googleblog.com/2020/12/mediapipe-holistic-simultaneous-face.html
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, D. Passos, M. Brucher, M. Perrot, E. Duchesnay, Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
S. Gautam, An improved mammogram classification approach using back propagation neural network, in Data Engineering and Intelligent Computing (Springer, Singapore, 2018), pp. 369–376
M. Navyasri, Robust features for emotion recognition from speech by using Gaussian mixture model classification, in Information and Communication Technology for Intelligent Systems (ICTIS 2017), vol 2 (Springer International Publishing, 2018), pp. 437–444
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Singh, A.K., Kumbhare, V.A., Arthi, K. (2022). Real-Time Human Pose Detection and Recognition Using MediaPipe. In: Reddy, V.S., Prasad, V.K., Wang, J., Reddy, K. (eds) Soft Computing and Signal Processing. ICSCSP 2021. Advances in Intelligent Systems and Computing, vol 1413. Springer, Singapore. https://doi.org/10.1007/978-981-16-7088-6_12
Download citation
DOI: https://doi.org/10.1007/978-981-16-7088-6_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7087-9
Online ISBN: 978-981-16-7088-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)