Li Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Li Wang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Menglin Zhou
School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo, China
2 shared publications - Nannan Zhang
School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo, China
2 shared publications - Xiaozhuo Xu
School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454150, China
2 shared publications - Yunji Zhao
Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment, Henan Polytechnic University, Jiaozuo, China
2 shared publications - Bo Su
School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo, China
1 shared publication - Guodong Wang
Massachusetts College of Liberal Arts
1 shared publication
Latest Publications
- Open Access
- 1 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (17) , 3702
Human Action Recognition Based on Skeleton Information and Multi-Feature Fusion
Action assessment and feedback can effectively assist fitness practitioners in improving exercise benefits. In this paper, we address key challenges in human action recognition and assessment by proposing innovative methods that enhance performance while reducing computational complexity. Firstly, we present Oct-MobileNet, a lightweight backbone network, to overcome the limitations of the traditional OpenPose algorithm’s VGG19 network, which exhibits a large parameter size and high device requirements. Oct-MobileNet employs octave convolution and attention mechanisms to improve the extraction of high-frequency features from the human body contour, resulting in enhanced accuracy with reduced model computational burden. Furthermore, we introduce a novel approach for action recognition that combines skeleton-based information and multiple feature fusion. By extracting spatial geometric and temporal characteristics from actions, we employ a sliding window algorithm to integrate these features. Experimental results show the effectiveness of our approach, demonstrating its ability to accurately recognize and classify various human actions. Additionally, we address the evaluation of traditional fitness exercises, specifically focusing on the BaDunJin movements. We propose a multimodal information-based assessment method that combines pose detection and keypoint analysis. Label sequences are obtained through a pose detector and each frame’s keypoint coordinates are represented as pose vectors. Leveraging multimodal information, including label sequences and pose vectors, we explore action similarity and perform quantitative evaluations to help exercisers assess the quality of their exercise performance.
- 1 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (17) , 3702
Open AccessHuman Action Recognition Based on Skeleton Information and Multi-Feature Fusion
Action assessment and feedback can effectively assist fitness practitioners in improving exercise benefits. In this paper, we address key challenges in human action recognition and assessment by proposing innovative methods that enhance performance while reducing computational complexity. Firstly, we present Oct-MobileNet, a lightweight backbone network, to overcome the limitations of the traditional OpenPose algorithm’s VGG19 network, which exhibits a large parameter size and high device requirements. Oct-MobileNet employs octave convolution and attention mechanisms to improve the extraction of high-frequency features from the human body contour, resulting in enhanced accuracy with reduced model computational burden. Furthermore, we introduce a novel approach for action recognition that combines skeleton-based information and multiple feature fusion. By extracting spatial geometric and temporal characteristics from actions, we employ a sliding window algorithm to integrate these features. Experimental results show the effectiveness of our approach, demonstrating its ability to accurately recognize and classify various human actions. Additionally, we address the evaluation of traditional fitness exercises, specifically focusing on the BaDunJin movements. We propose a multimodal information-based assessment method that combines pose detection and keypoint analysis. Label sequences are obtained through a pose detector and each frame’s keypoint coordinates are represented as pose vectors. Leveraging multimodal information, including label sequences and pose vectors, we explore action similarity and perform quantitative evaluations to help exercisers assess the quality of their exercise performance.
- 10 March 2023
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 18 (5) , 3839-3848
Bearing Fault Diagnosis of Single-Channel Data by a 3D DCN with Bilinear LBP and Modified KPCA
- 10 March 2023
- Published by Springer Nature in Journal of Electrical Engineering & Technology
- Vol. 18 (5) , 3839-3848
Bearing Fault Diagnosis of Single-Channel Data by a 3D DCN with Bilinear LBP and Modified KPCA
- 4 February 2022
- Published by Springer Nature in Control Theory and Technology
- Vol. 20 (1) , 103-113
Bearing fault diagnosis with cascaded space projection and a CNN
- 4 February 2022
- Published by Springer Nature in Control Theory and Technology
- Vol. 20 (1) , 103-113
Bearing fault diagnosis with cascaded space projection and a CNN
- 13 March 2012
- Published by Springer Nature
- p. 885-891
Research on Control System of Belt Conveyor in Coal Mine
- 13 March 2012
- Published by Springer Nature
- p. 885-891
Research on Control System of Belt Conveyor in Coal Mine