Pose Estimation Algorithm for Construction Workers
DOI:
https://doi.org/10.62051/ijcsit.v3n1.23Keywords:
Construction, DARK_HRNet, Pose estimationAbstract
In order to solve the problem of difficulty in judging the human posture of construction workers in complex environments, this paper uses the method based on bone points to identify the human posture, first produces a video dataset of construction workers, and then compares the two algorithms, and selects a suitable pose estimation algorithm for construction site scenarios, which contributes to the pose estimation of construction workers.
Downloads
References
Xiaohe Li, A Review of Two-Dimensional Human Pose Estimation [J]. Modern Computer, 2019, No.658(22):33-37.
Toshev A, Szegedy C. Deeppose: Human pose estimation via deep neuralnetworks [C]//Proceedings of the IEEE conference on computer vision and patternrecognition. 2014:1653-1660.
Chen Y, Wang Z, Peng Y, et al. Cascaded pyramid network for multi-person poseestimation [C]//Proceedings of the IEEE conference on computer vision and patternrecognition.2018:7103-7112.
Lin G, Milan A, Shen C, Reid I. Refinenet: multi-path refinc-ment networks for high-rcsolution semantic segmcntation. In: Proceedings of the 30th IEEE Conference on Computer Visionand Pattern Recognition.Honolulu, USA:IEEE, 2017.5168-5177
Fang H S, Xie S, Tai Y W, et al.Rmpe. Regional multi-person pose estimation [C]/IEEE IntermationalConference on Computer Vision. Piscataway: IEEE Computer Society, 2017:2334-2343.
Cao Z, Simon T, Wei S E, et al. Realtime multi-person 2d pose estimation using part affinity fields [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7291-7299.
Xu, S., Wang, X., Lv, W., Chang, Q., Cui, C., Deng, K., ... & Lai, B. (2022). PP-YOLOE: An evolved version of YOLO. arXiv preprint arXiv:2203.16250.
Zhang F, Zhu X, Dai H, et al. Distribution-aware coordinate representation for human pose estimation [C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 7093-7102.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
