Intelligent analysis method of dam material gradation for asphalt-core rock-fill dam based on enhanced Cascade Mask R-CNN and GCNet

Reasonable dam materials’ gradation design for asphalt-core rock-fill dams is one of the main ways to control permeability. It is a challenge to test whether it can meet the requirements of dam construction. The computer vision method provides a new idea for asphalt-core rock-fill dam material gradation testing. However, due to the characteristics of densely overlapping and multi-scale sizes of dam material particles, the traditional image segmentation methods and algorithms cannot achieve accurate segmentation of dam materials’ images, and it is hard to apply the segmentation result to quantify the gradation curve. In this research, the enhanced Cascade Mask R-CNN with ResNet and PAFPN (Path Aggregation Feature Pyramid Networks) is proposed. Multi-scale features extracted by ResNet and feature ensemble can be realized using PAFPN. Data augmentation (DA) and online hard example mining (OHEM) are also applied in segmentation model training. Moreover, the GCNet is proposed to calibrate the gradation curve. The nonlinear relationship between the real gradation and the one based on the segmentation results can be revealed and the model of dam materials’ gradation analysis can be established. In the research, the enhanced Cascade Mask R-CNN can achieve 84.2 mAP, which is higher than that of Cascade Mask R-CNN with 74.9 mAP. The effectiveness of the proposed module and training strategies is proved using ablation experiments. The average error of each level for the gradation calibration using GCNet is 0.55%, 1.87%, 2.22%, 1.18%, and 2.42% respectively. The accuracy can meet the requirements of hydraulic engineering construction, which verifies the effectiveness of the GCNet network for gradation calibration, and the research provides a new method and technology for intelligent gradation testing of the asphalt-core rock-fill dam.