Saved in:
Bibliographic Details
Main Authors: Lu, Peng, Jiang, Tao, Li, Yining, Li, Xiangtai, Chen, Kai, Yang, Wenming
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.07526
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910401122271232
author Lu, Peng
Jiang, Tao
Li, Yining
Li, Xiangtai
Chen, Kai
Yang, Wenming
author_facet Lu, Peng
Jiang, Tao
Li, Yining
Li, Xiangtai
Chen, Kai
Yang, Wenming
contents Real-time multi-person pose estimation presents significant challenges in balancing speed and precision. While two-stage top-down methods slow down as the number of people in the image increases, existing one-stage methods often fail to simultaneously deliver high accuracy and real-time performance. This paper introduces RTMO, a one-stage pose estimation framework that seamlessly integrates coordinate classification by representing keypoints using dual 1-D heatmaps within the YOLO architecture, achieving accuracy comparable to top-down methods while maintaining high speed. We propose a dynamic coordinate classifier and a tailored loss function for heatmap learning, specifically designed to address the incompatibilities between coordinate classification and dense prediction models. RTMO outperforms state-of-the-art one-stage pose estimators, achieving 1.1% higher AP on COCO while operating about 9 times faster with the same backbone. Our largest model, RTMO-l, attains 74.8% AP on COCO val2017 and 141 FPS on a single V100 GPU, demonstrating its efficiency and accuracy. The code and models are available at https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo.
format Preprint
id arxiv_https___arxiv_org_abs_2312_07526
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation
Lu, Peng
Jiang, Tao
Li, Yining
Li, Xiangtai
Chen, Kai
Yang, Wenming
Computer Vision and Pattern Recognition
Real-time multi-person pose estimation presents significant challenges in balancing speed and precision. While two-stage top-down methods slow down as the number of people in the image increases, existing one-stage methods often fail to simultaneously deliver high accuracy and real-time performance. This paper introduces RTMO, a one-stage pose estimation framework that seamlessly integrates coordinate classification by representing keypoints using dual 1-D heatmaps within the YOLO architecture, achieving accuracy comparable to top-down methods while maintaining high speed. We propose a dynamic coordinate classifier and a tailored loss function for heatmap learning, specifically designed to address the incompatibilities between coordinate classification and dense prediction models. RTMO outperforms state-of-the-art one-stage pose estimators, achieving 1.1% higher AP on COCO while operating about 9 times faster with the same backbone. Our largest model, RTMO-l, attains 74.8% AP on COCO val2017 and 141 FPS on a single V100 GPU, demonstrating its efficiency and accuracy. The code and models are available at https://github.com/open-mmlab/mmpose/tree/main/projects/rtmo.
title RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.07526