Huaneng Lancang River Hydropower Inc.

Tianjin University

Huaneng Group R &d Center Co Ltd

Hohai Univerdity

Bohui Pang

Haibin Xiao

Hao Chen

Xuexing Cao

Hua Zhou

Huan Zhao

Haodong Chen

Jiyuan Yu

Mai Meng

Fudong Chi

Rui Guo

Xu Wan

Shunbo Wang

Guangyao Wu

Yingchi Mao

An automatic concrete dam defect image description generation method based on graph attention network, including: 1) extract the local grid features and whole image features of the defect image and conduct image coding by using multi-layer convolutional neural network; 2) construct the grid feature interaction graph, and fuse and encode the grid visual features and global image features of the defect image; 3) update and optimize the global and local features through the graph attention network, and fully utilize the improved visual features for defect description. The invention constructs the grid feature interaction graph, updates the node information by using the graph attention network, and realizes the feature extraction task as the graph node classification task. The invention can capture the global image information of the defect image and the potential interaction of local grid features, and the generated description text can accurately and coherently describe the defect information.

Automatic concrete dam defect image description generation method based on graph attention network

The present disclosure relates to an automatic patrol inspection and intelligent erosion defect detection method and apparatus for a flood discharge tunnel, and belongs to the technical field of patrol inspection and defect detection. The method includes: constructing a flood discharge tunnel erosion defect database; constructing a flood discharge tunnel erosion defect analysis and evaluation standard and early warning threshold; performing automatic patrol inspection; and performing image analysis processing and intelligent recognition model training. According to the present disclosure, a condition of the flood discharge tunnel can undergo automatic patrol inspection, an erosion impact degree can be rapidly recognized and determined, the downstream life safety are not in danger during flood discharge, and a patrol inspection efficiency and a detection efficiency can be noticeably improved.

Automatic patrol inspection and intelligent erosion defect detection method and apparatus for flood discharge tunnel

Growing community of inventors

Yunnan, China

Bohui Pang