At present,the common 3D human pose es timation algorithms have achieved good results in representation learning,but th ere are still problems such as poor estimation accuracy at the joint points of the human skeleton.Therefore,how to effectively estimate human pose from a monocular RGB image using the redundant 2D pose sequence sptatio-temporal information is a different point in the research. In this paper,a 3D human pose estimation algorithm based on spati o-temporal multi-feature fusion network is proposed.The method utilizes a compact convolu tional neural network to learn spatio-temporal information to model the 2D joint position inf ormation as 3D joint position.The experimental results show that the method proposed in this paper can achieve relatively advanced end-to-end attitude estimation accuracy,and does not requ ire any attitude optimization method in the post-processing stage.The pose estimation obtained in this paper can effectively improve the average accuracy, which proves that the method in this paper can effectively improve the accuracy of human pose estimati on.