Shichu Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shichu Li has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Xiangyin Meng
School of Mechanical Engineering, Southwest Jiaotong University, Chengdu, China
3 shared publications - Huiping Huang
Jiuli Campus, School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China
2 shared publications - Lei Xie
Jiuli Campus, School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China
2 shared publications - Mushuai Wang
Jiuli Campus, School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China
2 shared publications - Yang Li
School of Institute of Smart City and Intelligent Transportation, Southwest Jiaotong University, Chengdu, China
2 shared publications - Huiping Huang
School of Mechanical Engineering, Southwest Jiaotong University, China
1 shared publication
Latest Publications
- Open Access
A Glove-Wearing Detection Algorithm Based on Improved YOLOv8
Wearing gloves during machinery operation in workshops is essential for preventing accidental injuries, such as mechanical damage and burns. Ensuring that workers are wearing gloves is a key strategy for accident prevention. Consequently, this study proposes a glove detection algorithm called YOLOv8-AFPN-M-C2f based on YOLOv8, offering swifter detection speeds, lower computational demands, and enhanced accuracy for workshop scenarios. This research innovates by substituting the head of YOLOv8 with the AFPN-M-C2f network, amplifying the pathways for feature vector propagation, and mitigating semantic discrepancies between non-adjacent feature layers. Additionally, the introduction of a superficial feature layer enriches surface feature information, augmenting the model’s sensitivity to smaller objects. To assess the performance of the YOLOv8-AFPN-M-C2f model, this study conducted multiple experiments using a factory glove detection dataset compiled for this study. The results indicate that the enhanced YOLOv8 model surpasses other network models. Compared to the baseline YOLOv8 model, the refined version shows a 2.6% increase in mAP@50%, a 63.8% rise in FPS, and a 13% reduction in the number of parameters. This research contributes an effective solution for the detection of glove adherence.
Open AccessA Glove-Wearing Detection Algorithm Based on Improved YOLOv8
Wearing gloves during machinery operation in workshops is essential for preventing accidental injuries, such as mechanical damage and burns. Ensuring that workers are wearing gloves is a key strategy for accident prevention. Consequently, this study proposes a glove detection algorithm called YOLOv8-AFPN-M-C2f based on YOLOv8, offering swifter detection speeds, lower computational demands, and enhanced accuracy for workshop scenarios. This research innovates by substituting the head of YOLOv8 with the AFPN-M-C2f network, amplifying the pathways for feature vector propagation, and mitigating semantic discrepancies between non-adjacent feature layers. Additionally, the introduction of a superficial feature layer enriches surface feature information, augmenting the model’s sensitivity to smaller objects. To assess the performance of the YOLOv8-AFPN-M-C2f model, this study conducted multiple experiments using a factory glove detection dataset compiled for this study. The results indicate that the enhanced YOLOv8 model surpasses other network models. Compared to the baseline YOLOv8 model, the refined version shows a 2.6% increase in mAP@50%, a 63.8% rise in FPS, and a 13% reduction in the number of parameters. This research contributes an effective solution for the detection of glove adherence.
- Open Access
- 2 November 2023
- Published by MDPI AG in Preprints.org
A Glove-wearing Detection Algorithm Based on Improved YOLOv8
Wearing gloves while operating machinery in workshops is an essential precaution to prevent mechanical injuries and burns from high temperatures, among other potential hazards. Ensuring workers are properly equipped with gloves, which is a crucial measure in accident prevention. Glove images often occupy a minimal proportion of the frame and are easily obscured by cluttered backgrounds, especially with limited edge computing resources. Consequently, this study proposes a glove detection algorithm called YOLOv8-AFPN-M-C2f based on YOLOv8, offering swifter detection speeds, lower computational demands, and enhanced accuracy for workshop scenarios. This research innovates by substituting the head of YOLOv8 with the AFPN-M-C2f network, amplifying the pathways for feature vector propagation, and mitigating semantic discrepancies between non-adjacent feature layers. Additionally, the introduction of a superficial feature layer enriches surface feature information, augmenting the model's sensitivity to smaller objects. To assess the performance of the YOLOv8-AFPN-M-C2f model, we conducted multiple experiments using a factory glove detection dataset compiled for this study. The results indicate that the enhanced YOLOv8 model surpasses other network models. Compared to the baseline YOLOv8 model, the refined version shows a 2.6% increase in mAP@50%, a 90.1% rise in FPS, and a 13% reduction in the number of parameters. This research contributes an effective solution for the detection of glove adherence.
- 2 November 2023
- Published by MDPI AG in Preprints.org
Open AccessA Glove-wearing Detection Algorithm Based on Improved YOLOv8
Wearing gloves while operating machinery in workshops is an essential precaution to prevent mechanical injuries and burns from high temperatures, among other potential hazards. Ensuring workers are properly equipped with gloves, which is a crucial measure in accident prevention. Glove images often occupy a minimal proportion of the frame and are easily obscured by cluttered backgrounds, especially with limited edge computing resources. Consequently, this study proposes a glove detection algorithm called YOLOv8-AFPN-M-C2f based on YOLOv8, offering swifter detection speeds, lower computational demands, and enhanced accuracy for workshop scenarios. This research innovates by substituting the head of YOLOv8 with the AFPN-M-C2f network, amplifying the pathways for feature vector propagation, and mitigating semantic discrepancies between non-adjacent feature layers. Additionally, the introduction of a superficial feature layer enriches surface feature information, augmenting the model's sensitivity to smaller objects. To assess the performance of the YOLOv8-AFPN-M-C2f model, we conducted multiple experiments using a factory glove detection dataset compiled for this study. The results indicate that the enhanced YOLOv8 model surpasses other network models. Compared to the baseline YOLOv8 model, the refined version shows a 2.6% increase in mAP@50%, a 90.1% rise in FPS, and a 13% reduction in the number of parameters. This research contributes an effective solution for the detection of glove adherence.
- Open Access
- 17 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Design and Kinematic Modeling of Grape Picking Robot Arm
Aiming at the application of robots in intelligent agriculture, this paper proposes a method of picking grapes by robots based on deep learning, uses depth camera for visual positioning of grapes, and designs a picking end-effector for picking tests. Picking experiments show that the method proposed in this paper has high detection accuracy, accurate grape rod positioning, high robot picking accuracy and good availability.
- 17 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessDesign and Kinematic Modeling of Grape Picking Robot Arm
Aiming at the application of robots in intelligent agriculture, this paper proposes a method of picking grapes by robots based on deep learning, uses depth camera for visual positioning of grapes, and designs a picking end-effector for picking tests. Picking experiments show that the method proposed in this paper has high detection accuracy, accurate grape rod positioning, high robot picking accuracy and good availability.