Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint

TL;DR

This paper introduces a hybrid multi-person pose estimation method that combines bottom-up feature extraction with top-down bounding box constraints, improving accuracy and robustness in challenging scenarios.

Contribution

It presents a novel approach integrating bottom-up and top-down techniques, enhancing pose estimation robustness to bounding box variations.

Findings

More accurate human pose estimation in challenging situations

Better time performance compared to existing methods

Robustness to bounding box shift and tightness

Abstract

In this work, we propose a new method for multi-person pose estimation which combines the traditional bottom-up and the top-down methods. Specifically, we perform the network feed-forwarding in a bottom-up manner, and then parse the poses with bounding box constraints in a top-down manner. In contrast to the previous top-down methods, our method is robust to bounding box shift and tightness. We extract features from an original image by a residual network and train the network to learn both the confidence maps of joints and the connection relationships between joints. During testing, the predicted confidence maps, the connection relationships and the bounding boxes are used to parse the poses of all persons. The experimental results showed that our method learns more accurate human poses especially in challenging situations and gains better time performance, compared with the bottom-up and the top-down methods.