1results about How to "High detection cost" patented technology

The present application belongs to the technical field of soil compaction degree prediction, and particularly relates to a soil compaction quality prediction method, medium and terminal based on image recognition, comprising the following steps: S10, collecting data of soil compaction degree and soil surface compaction pictures of sand under different conditions; S20, preprocessing the collected pictures, including picture normalization, grayscale and binarization processing, and constructing a data set; S30, constructing an improved CNN neural network model based on the preprocessed data set; S40, importing the data set into the improved CNN neural network model for pre-training to obtain a pre-training model; S50, importing the collected pictures into the pre-training model, and performing freezing and fine-tuning on the pre-training model to obtain a sand compaction quality prediction model; and S60, importing the preprocessed surface compaction pictures of the sand to be detected into the prediction model to output a compaction degree prediction value. The present application has simple process and convenient operation, the obtained prediction model has strong robustness and generalization ability, and the prediction efficiency and accuracy of sand compaction quality are high.