In light of the prevalent diseases of tunnel portals built in the harsh environment of the plateau region and the problems of low efficiency and high risk associated with traditional manual disease detection methods, a novel disease detection method for tunnel portals in the plateau region based on Unmanned Aerial Vehicle (UAV) image and deep learning was proposed. Firstly, an UAV was used to collect the disease images of a tunnel portal in the plateau region of Xinjiang, and a multi-disease semantic segmentation dataset was constructed. Then, based on DeeplabV3+, an improved model TP-DeeplabV3+ was proposed, which used MobileNetV2 as the backbone feature extraction network to reduce model parameters; Used Focal Loss as the loss function to solve the category imbalance problem in disease images; Used the CA attention mechanism to improve the segmentation performance; and proposed the disease quantification method. Experiment results show that TP-DeeplabV3+ attains 88.37% and 94.93% of mIoU and mPA on the test set, respectively. Furthermore, the model volume is reduced by 88.83%. The absolute error of the proposed disease quantification method for disease coverage rate is less than 0.3%, and the relative error is maintained below 7.31%. Compared with the traditional manual method, the proposed method facilitates the intelligent detection of tunnel portal safely and accurately in plateau region.