Menghui Ji
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Menghui Ji has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Fangtao Mao
Research Center for Humanoid Sensing, Intelligent Perception Research Institute, Zhejiang Laboratory, Hangzhou, China
1 shared publication - Haiyong Gan
National Institute of Metrology, Beijing 100029, China
1 shared publication - Haohao Xu
School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China
1 shared publication - Shuchang Xu
School of Information Science and Technology, Hangzhou Normal University, Hangzhou, Zhejiang 311121, China
1 shared publication - Wen Su
Zhejiang Sci-Tech University
1 shared publication - Wenzhen Yang
Zhejiang Laboratory
1 shared publication
Latest Publications
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-10
Flexible Material Quality Assessment Based on Visual–Tactile Fusion
Although vision-based defect detection has been widely applied in the industry, vision information alone is still insufficient for certain flexible materials such as leather, as their quality control may involve haptic properties. This article introduces a solution based on the fusion of vision and tactile data to evaluate the overall quality of flexible materials, such as leather. Firstly, a prototype equipment for capturing visual and tactile data is introduced. Specifically, the tactile data consists of XYZ-axis three components and is interpolated and visualized to align with the visual data. The aligned tactile data is then combined with the visual data and the derived defect segmentation map to form a cross-modal dataset. Additionally, a DeepLabv3+ derived network, which can be considered as a two-stream network with cross attention between visual and tactile data, is proposed to detect surface and non-surface defects. Experiments demonstrate that the proposed network exhibits a significant improvement of 10% compared to the vision-only network. The ablation study also examines the performance comparison of different fusion strategies. Furthermore, a grading strategy that integrates defect detection with haptic properties is finally introduced to assess the quality of flexible materials.
- 8 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-10
Flexible Material Quality Assessment Based on Visual–Tactile Fusion
Although vision-based defect detection has been widely applied in the industry, vision information alone is still insufficient for certain flexible materials such as leather, as their quality control may involve haptic properties. This article introduces a solution based on the fusion of vision and tactile data to evaluate the overall quality of flexible materials, such as leather. Firstly, a prototype equipment for capturing visual and tactile data is introduced. Specifically, the tactile data consists of XYZ-axis three components and is interpolated and visualized to align with the visual data. The aligned tactile data is then combined with the visual data and the derived defect segmentation map to form a cross-modal dataset. Additionally, a DeepLabv3+ derived network, which can be considered as a two-stream network with cross attention between visual and tactile data, is proposed to detect surface and non-surface defects. Experiments demonstrate that the proposed network exhibits a significant improvement of 10% compared to the vision-only network. The ablation study also examines the performance comparison of different fusion strategies. Furthermore, a grading strategy that integrates defect detection with haptic properties is finally introduced to assess the quality of flexible materials.