LiDAR intensity data can provide good spectral separation, which is an ideal data source applied to shield tunnel disease detection. In this paper, we take shield tunnel point cloud data as the research object and propose an intensity correction model based on a natural homogeneous target by analyzing the influencing factors of tunnel intensity information. And based on the corrected intensity data and the generated tunnel surface intensity image to achieve the detection of water seepage area. The experiments show that the model proposed in this paper can effectively eliminate the intensity deviation caused by distance and incidence angle and performs well in the coefficient of variation ratio, and the corrected intensity information of similar materials tends to be consistent. The actual water seepage area extracted based on the corrected intensity and the generated intensity image at 610640 m is 4.17 m², accounting for 1.05% of the total area of the interval, and 36 water leakage areas are correctly detected in this section of the tunnel, indicating that the water seepage disease areas can be effectively identified.