A Review on Human Pose Estimation
arXiv:2110.06877
Abstract
The phenomenon of Human Pose Estimation (HPE) is a problem that has been explored over the years, particularly in computer vision. But what exactly is it? To answer this, the concept of a pose must first be understood. Pose can be defined as the arrangement of human joints in a specific manner. Therefore, we can define the problem of Human Pose Estimation as the localization of human joints or predefined landmarks in images and videos. There are several types of pose estimation, including body, face, and hand, as well as many aspects to it. This paper will cover them, starting with the classical approaches to HPE to the Deep Learning based models.
References in corpus (8)
- High-Resolution Representations for Labeling Pixels and Regions
- Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
- AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
- Hand Pose Estimation: A Survey
- HandAugment: A Simple Data Augmentation Method for Depth-Based 3D Hand Pose Estimation
- VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
- A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video
- 3D Human Pose Estimation with 2D Marginal Heatmaps