2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints

TL;DR

This paper introduces a novel 2D human pose estimation approach that leverages explicit anatomical keypoint topology constraints to improve localization accuracy, and can enhance existing models like Lite-HRNet.

Contribution

The paper proposes a topology constraint term based on keypoint distances and directions, which can be integrated into existing pose estimation frameworks to boost their performance.

Findings

Achieved 2.9% AP improvement on COCO val2017 with Lite-HRNet

Achieved 3.3% AP improvement on COCO test-dev2017 with Lite-HRNet

Demonstrated the effectiveness of topology constraints in improving keypoint localization

Abstract

Recently, human pose estimation mainly focuses on how to design a more effective and better deep network structure as human features extractor, and most designed feature extraction networks only introduce the position of each anatomical keypoint to guide their training process. However, we found that some human anatomical keypoints kept their topology invariance, which can help to localize them more accurately when detecting the keypoints on the feature map. But to the best of our knowledge, there is no literature that has specifically studied it. Thus, in this paper, we present a novel 2D human pose estimation method with explicit anatomical keypoints structure constraints, which introduces the topology constraint term that consisting of the differences between the distance and direction of the keypoint-to-keypoint and their groundtruth in the loss object. More importantly, our proposed model can be plugged in the most existing bottom-up or top-down human pose estimation methods and improve their performance. The extensive experiments on the benchmark dataset: COCO keypoint dataset, show that our methods perform favorably against the most existing bottom-up and top-down human pose estimation methods, especially for Lite-HRNet, when our model is plugged into it, its AP scores separately raise by 2.9\% and 3.3\% on COCO val2017 and test-dev2017 datasets.