Fuente: WIPO "processing tomato" The invention discloses a tomato disease and insect pest real-time detection method and system based on deep learning, a computer and a storage medium, and relates to the field of deep learning intelligent agriculture. The problem that a traditional machine vision method is poor in robustness in a complex scene and difficult to meet working requirements in the complex scene is solved. The detection method comprises the following steps: acquiring a tomato leaf surface image by using a camera; according to the collected tomato leaf surface image, marking the category and position of diseases and pests; performing data enhancement processing according to the marked disease and insect pest categories and positions, and obtaining processed disease and insect pest data information; constructing a tomato disease and insect pest detection model according to the processed disease and insect pest data information; and performing tomato leaf surface image detection according to the tomato disease and insect pest detection model to obtain a detection result. The method is applied to the field of tomato disease and pest detection.