How Robust is 3D Human Pose Estimation to Occlusion?
arXiv:1808.09316
Abstract
Occlusion is commonplace in realistic human-robot shared environments, yet its effects are not considered in standard 3D human pose estimation benchmarks. This leaves the question open: how robust are state-of-the-art 3D pose estimation methods against partial occlusions? We study several types of synthetic occlusions over the Human3.6M dataset and find a method with state-of-the-art benchmark performance to be sensitive even to low amounts of occlusion. Addressing this issue is key to progress in applications such as collaborative and service robotics. We take a first step in this direction by improving occlusion-robustness through training data augmentation with synthetic occlusions. This also turns out to be an effective regularizer that is beneficial even for non-occluded test cases.
arXiv commentAccepted for IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'18) - Workshop on Robotic Co-workers 4.0: Human Safety and Comfort in Human-Robot Interactive Social Environments
References in corpus (8)
- Improved Regularization of Convolutional Neural Networks with Cutout
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- Random Erasing Data Augmentation
- Numerical Coordinate Regression with Convolutional Neural Networks
- Multi-Scale Structure-Aware Network for Human Pose Estimation
- Integral Human Pose Regression
- Modeling Visual Context is Key to Augmenting Object Detection Datasets
- 3D Human Pose Estimation with 2D Marginal Heatmaps
Cited by in corpus (7)
- Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation
- Real-Time Human Pose Estimation on a Smart Walker using Convolutional Neural Networks
- Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
- HandGCAT: Occlusion-Robust 3D Hand Mesh Reconstruction from Monocular Images
- HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation
- Hierarchical Kinematic Human Mesh Recovery
- Psychophysical Evaluation of Deep Re-Identification Models