Abstract
Recent advancements in computer vision have seen a rise in the prominence of applications using neural networks to understand human poses. However, while accuracy has been steadily increasing on State-of-the-Art datasets, these datasets often do not address the challenges seen in real-world applications. These challenges are dealing with people distant from the camera, people in crowds, and heavily occluded people. As a result, many real-world applications have trained on data that does not reflect the data present in deployment, leading to significant underperformance. This article presents ADG-Pose, a method for automatically generating datasets for real-world human pose estimation. These datasets can be customized to determine person distances, crowdedness, and occlusion distributions. Models trained with our method are able to perform in the presence of these challenges where those trained on other datasets fail. Using ADG-Pose, end-to-end accuracy for real-world skeleton-based action recognition sees a 20% increase on scenes with moderate distance and occlusion levels, and a 4X increase on distant scenes where other models failed to perform better than random.
Abstract (translated)
URL
https://arxiv.org/abs/2202.00753
