EHPE: Skeleton Cues-Based Gaussian Coordinate Encoding for Efficient Human Pose Estimation

doi:10.1109/TMM.2022.3197364

EHPE: Skeleton Cues-Based Gaussian Coordinate Encoding for Efficient Human Pose Estimation

2024-01-01

62

OA

AI

DOI：10.1109/TMM.2022.3197364

Original

Original request for help

Save

Abstract

En 中文

Human pose estimation (HPE) has many wide applications such as multimedia processing, behavior understanding and human-computer interaction. Most previous studies have encountered many constraints, such as restricted scenarios and RGB inputs. To mitigate constraints to estimating the human poses in general scenarios, we present an efficient human pose estimation model (i.e., EHPE) with joint direction cues and Gaussian coordinate encoding. Specifically, we propose an anisotropic Gaussian coordinate coding method to describe the skeleton direction cues among adjacent keypoints. To the best of our knowledge, this is the first time that the skeleton direction cues is introduced to the heatmap encoding in HPE task. Then, a multi-loss function is proposed to constrain the output to prevent the overfitting. The Kullback-Leibler divergence is introduced to measure the predication label and its ground truth one. The performance of EHPE is evaluated on two HPE datasets: MS COCO and MPII. Experimental results demonstrate that EHPE can obtain robust results, and it significantly outperforms existing state-of-the-art HPE methods. Lastly, we extend the experiments on infrared images captured by our research group. The experiments achieved the impressive results regardless of insufficient color and texture information.

Keywords:

Heating systems

Encoding

Biological system modeling

Task analysis

Pose estimation

Feature extraction

Skeleton

Deep learning

gaussian coordinate encoding

human pose estimation

regularization

skeleton direction

EHPE: Skeleton Cues-Based Gaussian Coordinate Encoding for Efficient Human Pose Estimation

Abstract

Journal

Organization