Saved in:
Bibliographic Details
Main Authors: Yu, Dongyang, Zhang, Haoyue, Zhao, Ruisheng, Chen, Guoqi, An, Wangpeng, Yang, Yanhong
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.09084
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916334465449984
author Yu, Dongyang
Zhang, Haoyue
Zhao, Ruisheng
Chen, Guoqi
An, Wangpeng
Yang, Yanhong
author_facet Yu, Dongyang
Zhang, Haoyue
Zhao, Ruisheng
Chen, Guoqi
An, Wangpeng
Yang, Yanhong
contents We present MovePose, an optimized lightweight convolutional neural network designed specifically for real-time body pose estimation on CPU-based mobile devices. The current solutions do not provide satisfactory accuracy and speed for human posture estimation, and MovePose addresses this gap. It aims to maintain real-time performance while improving the accuracy of human posture estimation for mobile devices. Our MovePose algorithm has attained an Mean Average Precision (mAP) score of 68.0 on the COCO \cite{cocodata} validation dataset. The MovePose algorithm displayed efficiency with a performance of 69+ frames per second (fps) when run on an Intel i9-10920x CPU. Additionally, it showcased an increased performance of 452+ fps on an NVIDIA RTX3090 GPU. On an Android phone equipped with a Snapdragon 8 + 4G processor, the fps reached above 11. To enhance accuracy, we incorporated three techniques: deconvolution, large kernel convolution, and coordinate classification methods. Compared to basic upsampling, deconvolution is trainable, improves model capacity, and enhances the receptive field. Large kernel convolution strengthens these properties at a decreased computational cost. In summary, MovePose provides high accuracy and real-time performance, marking it a potential tool for a variety of applications, including those focused on mobile-side human posture estimation. The code and models for this algorithm will be made publicly accessible.
format Preprint
id arxiv_https___arxiv_org_abs_2308_09084
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devices
Yu, Dongyang
Zhang, Haoyue
Zhao, Ruisheng
Chen, Guoqi
An, Wangpeng
Yang, Yanhong
Computer Vision and Pattern Recognition
Machine Learning
We present MovePose, an optimized lightweight convolutional neural network designed specifically for real-time body pose estimation on CPU-based mobile devices. The current solutions do not provide satisfactory accuracy and speed for human posture estimation, and MovePose addresses this gap. It aims to maintain real-time performance while improving the accuracy of human posture estimation for mobile devices. Our MovePose algorithm has attained an Mean Average Precision (mAP) score of 68.0 on the COCO \cite{cocodata} validation dataset. The MovePose algorithm displayed efficiency with a performance of 69+ frames per second (fps) when run on an Intel i9-10920x CPU. Additionally, it showcased an increased performance of 452+ fps on an NVIDIA RTX3090 GPU. On an Android phone equipped with a Snapdragon 8 + 4G processor, the fps reached above 11. To enhance accuracy, we incorporated three techniques: deconvolution, large kernel convolution, and coordinate classification methods. Compared to basic upsampling, deconvolution is trainable, improves model capacity, and enhances the receptive field. Large kernel convolution strengthens these properties at a decreased computational cost. In summary, MovePose provides high accuracy and real-time performance, marking it a potential tool for a variety of applications, including those focused on mobile-side human posture estimation. The code and models for this algorithm will be made publicly accessible.
title MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devices
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2308.09084