Pose Estimation Networks based on Graph Compressive Sensing

Gaofeng Li ； Songlin Wang

《International Core Journal of Engineering》 8卷1期 (2022/01) Pp. 475-481

https://doi.org/10.6919/ICJE.202201_8(1).0065

摘要

Pose estimation plays an important part in action recognition and behavior analysis. We present a novel graph compressive sensing model for pose estimation in 2D skeleton. Graph networks are designed for human pose features and movement of action with spatial information. Compressive sensing layer is incorporated into the framework of graph networks with pose sparsity in frames. The network layers parameters are compressively weighted. Pose prior emphasizes skeleton features learning for graph compressive sensing. Our model is simple and lightweight networks, appropriate for mobile and embedded machines. Experiment results show that the proposed networks effectively estimate pose in videos and outperform state-of-the-art methods.

關鍵字

Pose Estimation ； Compressive Sensing ； Graph Prior

參考文獻

S.E. Wei, V. Ramakrishna, T. Kanade, et al. Convolutional pose machines, IEEE CVPR, 2016.

Cao Z , Hidalgo G , Simon T , et al. OpenPose: Realtime multi-person 2D pose estimation using part affinity fields, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43 (2018), no. 1, p. 172-186.

M. Andriluka, L. Pishchulin, P. Gehler, et al. 2D human pose estimation: new benchmark and state of the art analysis, IEEE CVPR, 2014.

I. Henawy, K. Ahmed and H. Mahmoud. Action recognition using fast HOG3D of integral videos and Smith-Waterman partial matching, IET Image Processing, vol. 12 (2018), no. 6, p. 896-908.

Y. Tian, C. L. Zitnick and S. G. Narasimhan. Exploring the spatial hierarchy of mixture models for human pose estimation. IEEE ECCV, 2012.