针对盾构施工中渣石图像存在颗粒密集堆叠、尺寸差异大、边缘遮挡严重，导致语义分割方法在个体分割精度上受限的问题，提出一种基于改进Mask R-CNN的渣石几何特征识别模型。首先，构建包含实验室分散/堆叠场景与北京市南水北调配套工程团城湖至第九水厂（二期）工程不同地层场景的渣石图像数据集，采用数据增强扩充样本； 然后，通过对比试验确定以Mask R-CNN为基准模型，并引入高效多尺度注意力机制（EMA）增强骨干网络对多尺度特征的提取能力，同时采用Confluence-NMS算法替代传统非极大值抑制，降低密集场景下的误检与漏检； 最后，利用工程数据集进行消融试验。结果表明： 1）引入EMA与Confluence-NMS后，模型AP0.50、AP0.75、AP0.50∶0.95分别达到82.70%、73.69%、59.13%，较原始模型分别提升4.93%、3.19%和2.60%，F1-score提升3.63%，显著性检验证实改进效果显著； 2）基于分割掩膜，结合旋转卡壳算法与参照物换算，自动提取渣石的长短轴、面积、周长等几何特征； 3）在工程测试集上，模型预测的粒径分布与人工标注结果高度一致，长轴尺寸集中分布在25~75 mm，短轴尺寸集中分布在15~45 mm，各区间占比最大误差小于7.53%，仅在小粒径区间（<25 mm）因密集遮挡导致漏检而使误差略高； 4）泛化性能验证中，模型对青岛某隧道渣石图像的AP0.50∶0.95达57.62%，表明其具备跨工程适用性。
Semantic segmentation methods exhibit limited accuracy in the individual segmentation of rock chips due to dense stacking, large size variations, and severe edge occlusion in rock chip images collected during shield tunneling. To address these challenges, a rock chip geometric feature recognition model based on an improved mask region-based convolutional neural network (Mask R-CNN) is proposed. First, a rock chip image dataset is constructed, including laboratory (dispersed and stacked) and field scenarios from different strata of a tunneling project in Beijing, and data augmentation is applied to expand the sample size. Through comparative experiments, Mask R-CNN is selected as the baseline model. An efficient multiscale attention (EMA) mechanism is introduced to enhance the backbone network′s ability to extract multiscale features. Additionally, the Confluence-non-maximum suppression (Confluence-NMS) algorithm replaces the traditional non-maximum suppression method to reduce false detections and missed detections in dense scenarios. Ablation experiments conducted on the engineering dataset show that (1) after introducing EMA and Confluence-NMS, the model achieves AP0.50, AP0.75, and AP0.50∶0.95 values of 82.70%, 73.69%, and 59.13%, respectively, representing improvements of 4.93%, 3.19%, and 2.60% over the baseline model, while the F1-score increases by 3.63%; (2) significance tests confirm the statistical effectiveness of the proposed improvements. Based on the segmentation masks, the rotating calipers algorithm, combined with a reference-object conversion method, is used to automatically extract geometric features of rock chips, including the major and minor axis lengths, area, and perimeter. On the engineering test set, the particle size distribution predicted by the model is highly consistent with that obtained from manual annotations: the major axis lengths are primarily concentrated in the 25－75 mm range, while the minor axis lengths are mainly distributed within the 15－45 mm range. The maximum error in the proportion of each interval is less than 7.53%, with slightly higher errors occurring only in the small-size interval (<25 mm) due to missed detections caused by dense occlusion. In the evaluation of generalization performance, the model achieves an AP0.50∶0.95 of 57.62% on rock chip images from a tunnel project in Qingdao, demonstrating its cross-project applicability.
