A systematic survey on human pose estimation: upstream and downstream tasks, approaches, lightweight models, and prospects

Abstract In recent years, human pose estimation has been widely studied as a branch task of computer vision. Human pose estimation plays an important role in the development of medicine, fitness, virtual reality, and other fields. Early human pose estimation technology used traditional manual modeling methods. Recently, human pose estimation technology has developed rapidly using deep learning. This study not only reviews the basic research of human pose estimation but also summarizes the latest cutting-edge technologies. In addition to systematically summarizing the human pose estimation technology, this article also extends to the upstream and downstream tasks of human pose estimation, which shows the positioning of human pose estimation technology more intuitively. In particular, considering the issues regarding computer resources and challenges concerning model performance faced by human pose estimation, the lightweight human pose estimation models and the transformer-based human pose estimation models are summarized in this paper. In general, this article classifies human pose estimation technology around types of methods, 2D or 3D representation of outputs, the number of people, views, and temporal information. Meanwhile, classic datasets and targeted datasets are mentioned in this paper, as well as metrics applied to these datasets. Finally, we generalize the current challenges and possible development of human pose estimation technology in the future.