Guodong Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Guodong Li has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chengwei Li
School of Intelligent Equipment Engineering, Wuxi Taihu University, Wuxi, China
1 shared publication - Guili Peng
School of Control and Mechanical, Tianjin Chengjian University, Tianjin, China
1 shared publication - Huailei Chang
STECOL Corporation, Power Construction Corporation of China, Tianjin 300384, China
1 shared publication - Qinghua Wang
STECOL Corporation, Power Construction Corporation of China, Tianjin 300384, China
1 shared publication - Shoubin Wang
Tianjin Chengjian University
1 shared publication - Xiaofeng Bai
School of Instrument Science and Engineering, Harbin Institute of Technology, Harbin 150001, China
1 shared publication
Latest Publications
- Open Access
Semantic Segmentation of Surface Cracks in Urban Comprehensive Pipe Galleries Based on Global Attention
Cracks inside urban underground comprehensive pipe galleries are small and their characteristics are not obvious. Due to low lighting and large shadow areas, the differentiation between the cracks and background in an image is low. Most current semantic segmentation methods focus on overall segmentation and have a large perceptual range. However, for urban underground comprehensive pipe gallery crack segmentation tasks, it is difficult to pay attention to the detailed features of local edges to obtain accurate segmentation results. A Global Attention Segmentation Network (GA-SegNet) is proposed in this paper. The GA-SegNet is designed to perform semantic segmentation by incorporating global attention mechanisms. In order to perform precise pixel classification in the image, a residual separable convolution attention model is employed in an encoder to extract features at multiple scales. A global attention upsample model (GAM) is utilized in a decoder to enhance the connection between shallow-level features and deep abstract features, which could increase the attention of the network towards small cracks. By employing a balanced loss function, the contribution of crack pixels is increased while reducing the focus on background pixels in the overall loss. This approach aims to improve the segmentation accuracy of cracks. The comparative experimental results with other classic models show that the GA SegNet model proposed in this study has better segmentation performance and multiple evaluation indicators, and has advantages in segmentation accuracy and efficiency.
Open AccessSemantic Segmentation of Surface Cracks in Urban Comprehensive Pipe Galleries Based on Global Attention
Cracks inside urban underground comprehensive pipe galleries are small and their characteristics are not obvious. Due to low lighting and large shadow areas, the differentiation between the cracks and background in an image is low. Most current semantic segmentation methods focus on overall segmentation and have a large perceptual range. However, for urban underground comprehensive pipe gallery crack segmentation tasks, it is difficult to pay attention to the detailed features of local edges to obtain accurate segmentation results. A Global Attention Segmentation Network (GA-SegNet) is proposed in this paper. The GA-SegNet is designed to perform semantic segmentation by incorporating global attention mechanisms. In order to perform precise pixel classification in the image, a residual separable convolution attention model is employed in an encoder to extract features at multiple scales. A global attention upsample model (GAM) is utilized in a decoder to enhance the connection between shallow-level features and deep abstract features, which could increase the attention of the network towards small cracks. By employing a balanced loss function, the contribution of crack pixels is increased while reducing the focus on background pixels in the overall loss. This approach aims to improve the segmentation accuracy of cracks. The comparative experimental results with other classic models show that the GA SegNet model proposed in this study has better segmentation performance and multiple evaluation indicators, and has advantages in segmentation accuracy and efficiency.