A Review of Human Pose Estimation from Single Image
Naimat Ullah Khan, Wanggen Wan · 2018
Human pose estimation has been an important research topic for computer vision community. It has been in focus of researchers mainly because of its significant applications in various important fields like human computer interaction, action recognition, surveillance, picture understanding, threat prediction, etc. It's difficult to cover all aspects of this domain because of the diversity of its application areas, therefore this review is focused on the most significant contributions in Human Pose Estimation methods from a single two-dimensional image. We start our study with the traditional pictorial structure, go through a discussion of the use of Deep Neural Networks that improved the human pose estimation significantly and then the most recent, more famous approach namely Stacked Hourglass. Modern methods are based on training, evaluating and comparing on some common datasets using different architectures of Deep learning modules. Hence, starting from the first practical models for estimating human pose, we provide a comprehensive study of some of the most famous deep learning methods in order to provide a concise analytical review of these most influential methods.