Sewer line defect detection method and system based on confusion matrix

The invention discloses a sewer line defect detection method and system based on a confusion matrix. The method comprises the following steps: building an artificial neural network three-stage model; collecting a training data set and a verification data set to train an artificial neural network three-stage model; constructing a multi-classification percentage confusion matrix based on a training result and a real label, and determining an easy confusion category; and using a third-order model to finely classify the easy-to-confusion category, and correcting classification prediction of the easy-to-confusion category based on a fine classification result to obtain a final detection result. The system comprises a data acquisition module, a model construction module, a model training module, a prediction module, an easy-to-confuse coarse classification module, a fine classification module, a correction module and a post-processing module. By using the method, the problem of false positive sample increase caused