Portable Intelligent Detection of Coarse Aggregate Gradation Based on Stone-SAM
ZHANG Hong
YANG Junya
LIU Kexin
ZHANG Yipeng
CHENG Xuecong
Abstract：To achieve precise detection of coarse aggregate gradation,an intelligent portable detection method was proposed in this work.A knowledge distillation strategy was employed to lighten the network structure of the large visual model—segment anything model(SAM),and the neural network classifier high performance GPU network version 2(PP-HGNetV2)was embedded to provide the model with semantic judgment capabilities.A mathematical representation algorithm for the characteristic parameters of coarse aggregate particles was designed,and a mobile application was developed to enable high-throughput detection of coarse aggregate gradation.Tests were conducted on five different coarse aggregate gradation scenarios.The results indicate that the proposed method achieves higher segmentation accuracy for coarse aggregate particles compared to the original SAM model.It also precisely removes background information,and the extracted key parameters of coarse aggregate particles are accurate and reliable.
Keywords：segment anything model(SAM)coarse aggregate gradationintelligent detectionmobile terminalengineering inspection
Publication Date：2025-06-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：10( 581-590 )