This study proposes an innovative and field-friendly concrete forensic analysis technique. State-of-the-art encoder-decoder models are developed, trained and evaluated on a self-curated standard image dataset for segmenting gray-colored coarse aggregates within the same-colored concrete components. Contrary to existing practices, no color treatment or microscopy images are used to facilitate segmentation. A vision transformer-based (SwinTV2 + Segformer) model achieves the highest mIoU of 94.7%, surpassing the best-performing convolutional neural network-based (EfficientNetV2 + DeepLabV3+) model. Using segmented aggregate information, aggregate properties, i.e., area, size, and distance, are quantified using image processing methods. These properties are used to study the impact of varying supplementary cementitious materials and water-cement ratios on concrete segregation. Lastly, a forensic analysis technique is proposed for comparing and assessing the structural health of different samples within a specific member based on aggregate proportion in the mixture. The proposed method is validated by rigorous statistical analysis and promises broader applications in the real world.

中文翻译：

---

使用基于深度学习的粗骨料分割进行混凝土取证分析

这项研究提出了一种创新且现场友好的混凝土法医分析技术。最先进的编码器-解码器模型是在自行管理的标准图像数据集上开发、训练和评估的，用于分割相同颜色混凝土构件中的灰色粗骨料。与现有实践相反，没有使用颜色处理或显微镜图像来促进分割。基于视觉变压器（SwinTV2 + Segformer）的模型达到了 94.7% 的最高 mIoU，超过了性能最佳的基于卷积神经网络（EfficientNetV2 + DeepLabV3+）的模型。使用分段聚合信息，使用图像处理方法对聚合属性（即面积、大小和距离）进行量化。这些特性用于研究不同的辅助胶凝材料和水灰比对混凝土离析的影响。最后，提出了一种法医分析技术，用于根据混合物中的总比例来比较和评估特定成员内不同样本的结构健康状况。所提出的方法经过严格的统计分析验证，有望在现实世界中得到更广泛的应用。