Occluded Human Pose Estimation based on Limb Joint Augmentation
This addresses the generalization issue in occluded scenarios for pose estimation, but it is incremental as it builds on existing deep learning methods with augmentation and loss modifications.
The paper tackles the problem of human pose estimation under occlusion by proposing a limb joint augmentation framework, achieving significant performance improvements on OCHuman and CrowdPose datasets without extra inference cost.
Human pose estimation aims at locating the specific joints of humans from the images or videos. While existing deep learning-based methods have achieved high positioning accuracy, they often struggle with generalization in occlusion scenarios. In this paper, we propose an occluded human pose estimation framework based on limb joint augmentation to enhance the generalization ability of the pose estimation model on the occluded human bodies. Specifically, the occlusion blocks are at first employed to randomly cover the limb joints of the human bodies from the training images, imitating the scene where the objects or other people partially occlude the human body. Trained by the augmented samples, the pose estimation model is encouraged to accurately locate the occluded keypoints based on the visible ones. To further enhance the localization ability of the model, this paper constructs a dynamic structure loss function based on limb graphs to explore the distribution of occluded joints by evaluating the dependence between adjacent joints. Extensive experimental evaluations on two occluded datasets, OCHuman and CrowdPose, demonstrate significant performance improvements without additional computation cost during inference.