| |
| he task of human pose estimation has been largely improved most recently. However, there are still a lot of challenges to apply it in practice, such as the limited network bandwidth, the privacy and security risks and so on. In this paper, we propose a lightweight human pose estimation model called LCPN, which takes depthwise separable convolution instead of standard convolution to lighten the network. Besides, we try to combine the heatmap prediction and coordinate regression in the keypoint prediction stage, which will further improve the efficiency of the network. The proposed approach achieves an excellent trade-off between speed and accuracy on the LSP and MPII datasets, and is very suitable to run on edge devices with lower computing power. |
|
| Keywords:Computer science and technology; Human pose estimation; Lightweight model; Edge computation |
|
