Optimization Method of Human Posture Recognition Based on Kinect V2 Sensor
Human action recognition aims to understand human behavior and is crucial in enhancing the intelligence and naturalness of human–computer interaction and bionic robots. This paper proposes a method to improve the complexity and real-time performance of action recognition by combining the Kinect sens...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/4/254 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850183225961349120 |
|---|---|
| author | Hang Li Hao Li Ying Qin Yiming Liu |
| author_facet | Hang Li Hao Li Ying Qin Yiming Liu |
| author_sort | Hang Li |
| collection | DOAJ |
| description | Human action recognition aims to understand human behavior and is crucial in enhancing the intelligence and naturalness of human–computer interaction and bionic robots. This paper proposes a method to improve the complexity and real-time performance of action recognition by combining the Kinect sensor with the OpenPose algorithm, the Levenberg–Marquardt (LM) algorithm, and the Dynamic Time Warping (DTW) algorithm. First, the Kinect V2 depth sensor is used to capture color images, depth images, and 3D skeletal point information from the human body. Next, the color image is processed using OpenPose to extract 2D skeletal point information, which is then mapped to the depth image to obtain 3D skeletal point information. Subsequently, the LM algorithm is employed to fuse the 3D skeletal point sequences with the sequences obtained from Kinect, generating stable 3D skeletal point sequences. Finally, the DTW algorithm is utilized to recognize complex movements. Experimental results across various scenes and actions demonstrate that the method is stable and accurate, achieving an average recognition rate of 95.94%. The method effectively addresses issues, such as jitter and self-occlusion, when Kinect collects skeletal points. The robustness and accuracy of the method make it highly suitable for application in robot interaction systems. |
| format | Article |
| id | doaj-art-d6cb74acf42b4e48bfb959c17856d347 |
| institution | OA Journals |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-d6cb74acf42b4e48bfb959c17856d3472025-08-20T02:17:25ZengMDPI AGBiomimetics2313-76732025-04-0110425410.3390/biomimetics10040254Optimization Method of Human Posture Recognition Based on Kinect V2 SensorHang Li0Hao Li1Ying Qin2Yiming Liu3School of Information Engineering, Xi’an University, Xi’an 710065, ChinaSchool of Information Engineering, Xi’an University, Xi’an 710065, ChinaXi’an Longviews Electronic Engineering Co., Ltd., Xi’an 710048, ChinaKey Laboratory of Spectral Imaging Technology, Xi’an Institute of Optics and Precision Mechanics, Xi’an 710119, ChinaHuman action recognition aims to understand human behavior and is crucial in enhancing the intelligence and naturalness of human–computer interaction and bionic robots. This paper proposes a method to improve the complexity and real-time performance of action recognition by combining the Kinect sensor with the OpenPose algorithm, the Levenberg–Marquardt (LM) algorithm, and the Dynamic Time Warping (DTW) algorithm. First, the Kinect V2 depth sensor is used to capture color images, depth images, and 3D skeletal point information from the human body. Next, the color image is processed using OpenPose to extract 2D skeletal point information, which is then mapped to the depth image to obtain 3D skeletal point information. Subsequently, the LM algorithm is employed to fuse the 3D skeletal point sequences with the sequences obtained from Kinect, generating stable 3D skeletal point sequences. Finally, the DTW algorithm is utilized to recognize complex movements. Experimental results across various scenes and actions demonstrate that the method is stable and accurate, achieving an average recognition rate of 95.94%. The method effectively addresses issues, such as jitter and self-occlusion, when Kinect collects skeletal points. The robustness and accuracy of the method make it highly suitable for application in robot interaction systems.https://www.mdpi.com/2313-7673/10/4/254human–computer interactionhuman action recognitionbone point optimization |
| spellingShingle | Hang Li Hao Li Ying Qin Yiming Liu Optimization Method of Human Posture Recognition Based on Kinect V2 Sensor Biomimetics human–computer interaction human action recognition bone point optimization |
| title | Optimization Method of Human Posture Recognition Based on Kinect V2 Sensor |
| title_full | Optimization Method of Human Posture Recognition Based on Kinect V2 Sensor |
| title_fullStr | Optimization Method of Human Posture Recognition Based on Kinect V2 Sensor |
| title_full_unstemmed | Optimization Method of Human Posture Recognition Based on Kinect V2 Sensor |
| title_short | Optimization Method of Human Posture Recognition Based on Kinect V2 Sensor |
| title_sort | optimization method of human posture recognition based on kinect v2 sensor |
| topic | human–computer interaction human action recognition bone point optimization |
| url | https://www.mdpi.com/2313-7673/10/4/254 |
| work_keys_str_mv | AT hangli optimizationmethodofhumanposturerecognitionbasedonkinectv2sensor AT haoli optimizationmethodofhumanposturerecognitionbasedonkinectv2sensor AT yingqin optimizationmethodofhumanposturerecognitionbasedonkinectv2sensor AT yimingliu optimizationmethodofhumanposturerecognitionbasedonkinectv2sensor |