Research Progress of Deep Learning Methods in Two-dimensional Human Pose Estimation
The task of human pose estimation is to locate and detect the key points of human body in images or videos.It has always been one of the hot research directions in the field of computer vision,and it is also a key step for computers to understand human actions.In recent years,it has wide application...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial office of Computer Science
2022-12-01
|
| Series: | Jisuanji kexue |
| Subjects: | |
| Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-12-219.pdf |
| _version_ | 1797845114299613184 |
|---|---|
| author | ZHANG Guo-ping, MA Nan, Guan Huai-guang, WU Zhi-xuan |
| author_facet | ZHANG Guo-ping, MA Nan, Guan Huai-guang, WU Zhi-xuan |
| author_sort | ZHANG Guo-ping, MA Nan, Guan Huai-guang, WU Zhi-xuan |
| collection | DOAJ |
| description | The task of human pose estimation is to locate and detect the key points of human body in images or videos.It has always been one of the hot research directions in the field of computer vision,and it is also a key step for computers to understand human actions.In recent years,it has wide application for predicting the poses of two-dimensional human body key points in images and videos.Using the powerful image feature extraction capabilities of deep learning,two-dimensional human pose estimation has been improved in robustness,accuracy,and processing time,and the performance effect is far beyond traditional methods.According to the different number of objects in the two-dimensional human body pose,it can be divided into single-person and multi-person pose estimation methods.For single-person pose estimation,according to the different representations of the extracted key points,coordinate regression methods based on the direct prediction of human coordinate points and heat map detection methods based on predicting the Gaussian distribution of human key points can be used.In multi-person pose estimation,it is divided into the top-down method which solves the process from multiple people to a single person,and a bottom-up method that directly deals with the key points of multiple people.Based on the existing estimation methods of human body posture,this paper analyzes the internal mechanism of the network structure,analyzes the commonly used datasets and evaluation indicators,and elaborates the current problems and future development trends. |
| first_indexed | 2024-04-09T17:33:21Z |
| format | Article |
| id | doaj.art-2a92fa07454f4f1f8b6648b8989ffd96 |
| institution | Directory Open Access Journal |
| issn | 1002-137X |
| language | zho |
| last_indexed | 2024-04-09T17:33:21Z |
| publishDate | 2022-12-01 |
| publisher | Editorial office of Computer Science |
| record_format | Article |
| series | Jisuanji kexue |
| spelling | doaj.art-2a92fa07454f4f1f8b6648b8989ffd962023-04-18T02:32:59ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2022-12-01491221922810.11896/jsjkx.210900041Research Progress of Deep Learning Methods in Two-dimensional Human Pose EstimationZHANG Guo-ping, MA Nan, Guan Huai-guang, WU Zhi-xuan01 Beijing Key Laboratory of Information Service Engineering,Beijing Union University,Beijing 100101,China ;2 Department of Information Science,Beijing University of Technology,Beijing 100124,China ;3 College of Robotics,Beijing Union University,Beijing 100101,ChinaThe task of human pose estimation is to locate and detect the key points of human body in images or videos.It has always been one of the hot research directions in the field of computer vision,and it is also a key step for computers to understand human actions.In recent years,it has wide application for predicting the poses of two-dimensional human body key points in images and videos.Using the powerful image feature extraction capabilities of deep learning,two-dimensional human pose estimation has been improved in robustness,accuracy,and processing time,and the performance effect is far beyond traditional methods.According to the different number of objects in the two-dimensional human body pose,it can be divided into single-person and multi-person pose estimation methods.For single-person pose estimation,according to the different representations of the extracted key points,coordinate regression methods based on the direct prediction of human coordinate points and heat map detection methods based on predicting the Gaussian distribution of human key points can be used.In multi-person pose estimation,it is divided into the top-down method which solves the process from multiple people to a single person,and a bottom-up method that directly deals with the key points of multiple people.Based on the existing estimation methods of human body posture,this paper analyzes the internal mechanism of the network structure,analyzes the commonly used datasets and evaluation indicators,and elaborates the current problems and future development trends.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-12-219.pdftwo-dimensional human pose estimation|deep learning|single-person pose estimation|multi-person pose estimation|evaluation metrics |
| spellingShingle | ZHANG Guo-ping, MA Nan, Guan Huai-guang, WU Zhi-xuan Research Progress of Deep Learning Methods in Two-dimensional Human Pose Estimation Jisuanji kexue two-dimensional human pose estimation|deep learning|single-person pose estimation|multi-person pose estimation|evaluation metrics |
| title | Research Progress of Deep Learning Methods in Two-dimensional Human Pose Estimation |
| title_full | Research Progress of Deep Learning Methods in Two-dimensional Human Pose Estimation |
| title_fullStr | Research Progress of Deep Learning Methods in Two-dimensional Human Pose Estimation |
| title_full_unstemmed | Research Progress of Deep Learning Methods in Two-dimensional Human Pose Estimation |
| title_short | Research Progress of Deep Learning Methods in Two-dimensional Human Pose Estimation |
| title_sort | research progress of deep learning methods in two dimensional human pose estimation |
| topic | two-dimensional human pose estimation|deep learning|single-person pose estimation|multi-person pose estimation|evaluation metrics |
| url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-12-219.pdf |
| work_keys_str_mv | AT zhangguopingmananguanhuaiguangwuzhixuan researchprogressofdeeplearningmethodsintwodimensionalhumanposeestimation |