Multi-Person Pose Estimation Using Group-Based Convolutional Neural Network Model
Human pose estimation has drawn extensive attention recently and there has been significant progress on it due to the rising popularity of convolutional neural networks (CNN). However, existing state-of-the-art approaches suffer from occlusion, complicated backgrounds, and substantial position fluct...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10110984/ |
_version_ | 1797832746662363136 |
---|---|
author | Shuhena Salam Aonty Kaushik Deb Moumita Sen Sarma Pranab Kumar Dhar Tetsuya Shimamura |
author_facet | Shuhena Salam Aonty Kaushik Deb Moumita Sen Sarma Pranab Kumar Dhar Tetsuya Shimamura |
author_sort | Shuhena Salam Aonty |
collection | DOAJ |
description | Human pose estimation has drawn extensive attention recently and there has been significant progress on it due to the rising popularity of convolutional neural networks (CNN). However, existing state-of-the-art approaches suffer from occlusion, complicated backgrounds, and substantial position fluctuations because of disregarding the human body form. Human parsing is a very pertinent activity that can provide crucial semantic data about bodily parts for position estimation. To overcome the aforesaid limitations, this paper introduces a human pose estimation method using a group-based convolutional neural network model. The proposed method adopts a bottom-up parsing strategy that yields features to extract skeletal key points in the human body. Moreover, it creates a grouping of anatomical key points for individuals by utilizing the non-parametric description for the key point association vector field. Experimental results indicate that the proposed method provides superior performance than the state-of-the-art algorithms in terms of accuracy. In addition, it optimizes its output and detects occluded as well as invisible key points by incorporating feature representation. The proposed method surpasses the recent methods, achieving 93% of the mean average accuracy. |
first_indexed | 2024-04-09T14:13:51Z |
format | Article |
id | doaj.art-27cef1fed4f4485c8dbc0f14ccf8ce11 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-09T14:13:51Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-27cef1fed4f4485c8dbc0f14ccf8ce112023-05-05T23:00:29ZengIEEEIEEE Access2169-35362023-01-0111423434236010.1109/ACCESS.2023.327159310110984Multi-Person Pose Estimation Using Group-Based Convolutional Neural Network ModelShuhena Salam Aonty0https://orcid.org/0000-0002-1335-7530Kaushik Deb1https://orcid.org/0000-0002-7345-0999Moumita Sen Sarma2Pranab Kumar Dhar3https://orcid.org/0000-0002-9664-3056Tetsuya Shimamura4Department of Computer Science and Engineering, Chittagong University of Engineering and Technology (CUET), Chattogram, BangladeshDepartment of Computer Science and Engineering, Chittagong University of Engineering and Technology (CUET), Chattogram, BangladeshDepartment of Computer Science and Engineering, Chittagong University of Engineering and Technology (CUET), Chattogram, BangladeshDepartment of Computer Science and Engineering, Chittagong University of Engineering and Technology (CUET), Chattogram, BangladeshDepartment of Information and Computer Sciences, Saitama University, 255 Shimo-Okubo, Sakura-ku, Saitama, JapanHuman pose estimation has drawn extensive attention recently and there has been significant progress on it due to the rising popularity of convolutional neural networks (CNN). However, existing state-of-the-art approaches suffer from occlusion, complicated backgrounds, and substantial position fluctuations because of disregarding the human body form. Human parsing is a very pertinent activity that can provide crucial semantic data about bodily parts for position estimation. To overcome the aforesaid limitations, this paper introduces a human pose estimation method using a group-based convolutional neural network model. The proposed method adopts a bottom-up parsing strategy that yields features to extract skeletal key points in the human body. Moreover, it creates a grouping of anatomical key points for individuals by utilizing the non-parametric description for the key point association vector field. Experimental results indicate that the proposed method provides superior performance than the state-of-the-art algorithms in terms of accuracy. In addition, it optimizes its output and detects occluded as well as invisible key points by incorporating feature representation. The proposed method surpasses the recent methods, achieving 93% of the mean average accuracy.https://ieeexplore.ieee.org/document/10110984/Pose estimationconvolutional neural networkocclusionbottom-up parsingskeletal keypoint |
spellingShingle | Shuhena Salam Aonty Kaushik Deb Moumita Sen Sarma Pranab Kumar Dhar Tetsuya Shimamura Multi-Person Pose Estimation Using Group-Based Convolutional Neural Network Model IEEE Access Pose estimation convolutional neural network occlusion bottom-up parsing skeletal keypoint |
title | Multi-Person Pose Estimation Using Group-Based Convolutional Neural Network Model |
title_full | Multi-Person Pose Estimation Using Group-Based Convolutional Neural Network Model |
title_fullStr | Multi-Person Pose Estimation Using Group-Based Convolutional Neural Network Model |
title_full_unstemmed | Multi-Person Pose Estimation Using Group-Based Convolutional Neural Network Model |
title_short | Multi-Person Pose Estimation Using Group-Based Convolutional Neural Network Model |
title_sort | multi person pose estimation using group based convolutional neural network model |
topic | Pose estimation convolutional neural network occlusion bottom-up parsing skeletal keypoint |
url | https://ieeexplore.ieee.org/document/10110984/ |
work_keys_str_mv | AT shuhenasalamaonty multipersonposeestimationusinggroupbasedconvolutionalneuralnetworkmodel AT kaushikdeb multipersonposeestimationusinggroupbasedconvolutionalneuralnetworkmodel AT moumitasensarma multipersonposeestimationusinggroupbasedconvolutionalneuralnetworkmodel AT pranabkumardhar multipersonposeestimationusinggroupbasedconvolutionalneuralnetworkmodel AT tetsuyashimamura multipersonposeestimationusinggroupbasedconvolutionalneuralnetworkmodel |