Human Posture Estimation

With the development of the artificial intelligence field, automatic drive, and machine learning, both did well in their field. Human posture estimation could help people in many cases, as an imitation of the human body, entertainment, sports, and other field have had some achievement, also shows the importance of human posture estimation for the future. In 2013, Toshev introduced Deep Pose into human posture estimation, and the study of human body posture estimation began to shift from traditional methods to Deep learning. CNN was firstly proposed to be applied to the detection of human joints and transform the estimation of human body posture into the regression problem of joints. Secondly, CPM mainly uses Heatmap to represent joints' position and position constraint relationship, which can fully consider the spatial position relationship between various joints. Then in the process of top to bottom and bottom to top in Hourglass, through convolution and pooling, the image's resolution is adjusted to the best, and the information of the image is integrated. CPN also uses the top-down method to detect the body frame first and detect the human body nodes in the body frame. RefineNet can correct the results with large errors. HRNET is the follow-up to Simple Baseline, which enables multiscale fusion through information exchange across resolution subnetworks. We discussed a lot about human posture. Deep learning has led to the rapid development of academy and technology. The development of technology will improve our future analysis on human detection data, for example, detect our daily walking state, or in different occasions through images and other data to analyze the characteristics of the human posture. This will help us develop in the future, which will have a crucial impact on our development.