Tobacco leaf baking temperature and humidity key point discrimination method, medium and system

The invention provides a tobacco leaf curing temperature and humidity key point discrimination method, medium and system, and belongs to the technical field of intelligent tobacco leaf curing, the multi-scale enhancement layer tobacco leaf curing temperature and humidity key point discrimination method comprises the following steps: obtaining a cured tobacco leaf image; a feature mapping module is used for conducting filtering processing on the flue-cured tobacco leaf image, and initial mapping features are extracted; using an enhanced mapping feature module to extract detail features of the flue-cured tobacco leaf image; extracting high-level semantic features from the flue-cured tobacco image by using an enhanced mapping feature module; inputting the initial mapping features, the detail features and the semantic features into a feature fusion module; extracting context features of the high-level semantic features; generating multi-scale features by using the context features, the detail features and the enh