Abstract
Pose estimation is an artificial intelligence and computer vision approach. Human Posture Estimate is a more advanced version of pose estimation technology that graphically depicts the position and orientation of a human body. It's one of the most appealing fields of research, and it's gaining popularity thanks to its practicality and versatility—utilized in a range of industries, including gaming, healthcare, agriculture, augmented reality, and sports. This research project intends to establish a deep learning-based human posture identification system that can be used to identify diverse agricultural operations, with the intention of introducing the concept of automation into the agriculture field. A proprietary dataset of farmer postures is used to run this system. The picture from the dataset is pre-processed before a deep neural network is used to detect body points in the image, and OpenCV creates a graphical representation of the points. The angle between body components is crucial in determining posture, which is derived from various calculations. Finally, the result is compared to a threshold value before being processed. Our model could accurately measure a farmer's or human's posture in three major categories: sitting, bending, and standing with a test accuracy of about 77%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. İn: Proceedings of IEEE Computer Social Conference Computer Vision and Pattern Recognition, pp. 1653–1660 (2014). https://doi.org/10.1109/CVPR.2014.214
Wang, J., et al.: Deep 3D human pose estimation: a review. Comput. Vision Image Underst. 210, 103225 (2021). https://doi.org/10.1016/j.cviu.2021.103225
Akhter, I., Black, M.J.: Pose-conditioned joint angle limits for 3D human pose reconstruction. In: Proceedings of IEEE Computer Socity Conference on Computer Vision and Pattern Recognition, vol. 07–12-June, pp. 1446–1455 (2015). https://doi.org/10.1109/CVPR.2015.7298751
Guler, R.A., Neverova, N., Kokkinos, I.: DensePose: dense human pose estimation ın thewild. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition, pp. 7297–7306 (2016). http://arxiv.org/abs/1612.01202
Andriluka, M., et al.: PoseTrack: a benchmark for human pose estimation and tracking. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 5167–5176 (2018). https://doi.org/10.1109/CVPR.2018.00542
Liu, Y., Xu, Y., Li, S.B.: 2-D human pose estimation from ımages based on deep learning: a review. In: Proceedings of 2018 2nd IEEE Advances in Information Management Communication, Electronics and Automation Control Conference, IMCEC 2018, no. Imcec, pp. 462–465 (2018). https://doi.org/10.1109/IMCEC.2018.8469573
Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: New benchmark and state of the art analysis. İn: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3686–3693 (2014). https://doi.org/10.1109/CVPR.2014.471
Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 172–186 (2021). https://doi.org/10.1109/TPAMI.2019.2929257
Wei, S.-E., Ramakrishna, V., Kanada, T., Sheikh, Y.: Pose machines. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition (2016)
Li, S., Chan, A.B.: 3D human pose estimation from monocular images with deep convolutional neural network. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9004, pp. 332–347. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16808-1_23
Park, S., Ji, M., Chun, J.: 2D human pose estimation based on object detection using RGB-D information. KSII Trans. Internet Inf. Syst. 12(2), 800–816 (2018). https://doi.org/10.3837/tiis.2018.02.015
Moreno-Noguer, F.: 3D human pose estimation from a single image via distance matrix regression. In: Proceedings - 30th IEEE Conference on Computer Vision Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 1561–1570 (2017). https://doi.org/10.1109/CVPR.2017.170
Brau, E., Jiang, H.: 3D human pose estimation via deep learning from 2D annotations. In: Proceedings - 2016 4th International Conference 3D Vision, 3DV 2016, pp. 582–591 (2016). https://doi.org/10.1109/3DV.2016.84
Sungheetha, A., Rajesh Sharma, R.: Classification of remote sensing ımage scenes using double feature extraction hybrid deep learning approach. J. Inf. Technol. Digital World 3(2), 133–149 (2021). https://doi.org/10.36548/jitdw.2021.2.006
Karuppusamy, P.: Building detection using two-layered novel convolutional neural networks. J. Soft Comput. Paradigm 3(1), 29–37 (2021). https://doi.org/10.36548/jscp.2021.1.004
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 Switzerland AG
About this paper
Cite this paper
Meharaj-Ul-Mahmmud, Ahmed, M.A., Alam, S.M., Imam, O.T., Reza, A.W., Arefin, M.S. (2022). Human Posture Estimation: In Aspect of the Agriculture Industry. In: Chen, J.IZ., Tavares, J.M.R.S., Shi, F. (eds) Third International Conference on Image Processing and Capsule Networks. ICIPCN 2022. Lecture Notes in Networks and Systems, vol 514. Springer, Cham. https://doi.org/10.1007/978-3-031-12413-6_38
Download citation
DOI: https://doi.org/10.1007/978-3-031-12413-6_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12412-9
Online ISBN: 978-3-031-12413-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)