基于深度学习的人体姿态估计方法综述

基于深度学习的人体姿态估计方法旨在通过构建合适的神经网络,直接从二维的图像特征中回归出人体姿态信息。主要按照2D人体姿态估计到3D人体姿态估计的顺序,并从单人检测与多人检测、稀疏的关节点检测与密集的模型构建等方面,对近年来基于深度学习的人体姿态估计方法进行系统介绍,从而初步了解如何通过深度学习的方法得到人体姿态的各个要素,包括肢体部件的相对朝向和比例尺度、骨骼关节点的位置坐标和连接关系,甚至更为复杂的人体蒙皮模型信息。最后,对当前研究面临的挑战以及未来的热点动向进行概述,清晰地呈现出该领域的发展脉络。

Overview of Human Pose Estimation Methods Based on Deep Learning

Human pose estimation is a research hot point in the field of computer vision. The human pose estimation methods based on deep learning get directly human pose information from two-dimensional image features through an appropriate neural network. This paper mainly follows the sequence from 2D to 3D human pose estimation, from the single-person detection to multi-person detection, from sparse node detection to dense model building, has systematically introduced the human post estimation methods in recent years based on deep learning to give a preliminary understanding of how to acquire the elements of human pose through deep learning, including the relative orientation and ratio scale of limb parts, the position coordinates and connection relations of joint points, and the information of the even more complex human skin model information. In the end, it summarizes the current research challenges and future hot point trends, which clearly present the development venation of this field for readers.