Human Pose Estimation Based on Multi-branch Convolutional Neural Network
Haochen Zhang, Hailun Xia, Rui Zhang, Caili Guo · 2022 IEEE 2nd International Conference on Power, Electronics and Computer Applications (ICPECA) · 2022
With the development of the convolutional neural network, significant progress has been made in human pose estimation. Recent human pose estimation approaches adopt a single branch network, which can only provide limited surveillance information. Aiming at the problem, we propose to adopt a multi-branch network for both 2D human pose estimation and 3D human pose estimation. Leading results on multiple datasets verify the effectiveness of our multi-branch network.