期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 43, 期 1, 页码 172-186出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2019.2929257
关键词
2D human pose estimation; 2D foot keypoint estimation; real-time; multiple person; part affinity fields
资金
- Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior/Interior Business Center (DOI/IBC) [D17PC00340]
This work presents a real-time approach to detect the 2D pose of multiple people in an image, achieving high accuracy and real-time performance regardless of the number of people in the image. By refining PAFs separately, both runtime performance and accuracy are significantly improved. Additionally, the first combined body and foot keypoint detector reduces inference time and maintains accuracy compared to running them sequentially.
Realtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. This bottom-up system achieves high accuracy and realtime performance, regardless of the number of people in the image. In previous work, PAFs and body part location estimation were refined simultaneously across training stages. We demonstrate that a PAF-only refinement rather than both PAF and body part location refinement results in a substantial increase in both runtime performance and accuracy. We also present the first combined body and foot keypoint detector, based on an internal annotated foot dataset that we have publicly released. We show that the combined detector not only reduces the inference time compared to running them sequentially, but also maintains the accuracy of each component individually. This work has culminated in the release of Open Pose, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据