Fuente: WIPO "tobacco agriculture" The invention discloses a tobacco field planting information extraction method based on an unmanned aerial vehicle remote sensing image. The method comprises the following steps: establishing a tobacco detection deep learning model; shooting image data of the to-be-detected tobacco field through the unmanned aerial vehicle; inputting the image data into the tobacco detection deep learning model to obtain a plurality of single tobacco detection frames; clustering and dividing different tobacco fields, and extracting planting information of each tobacco field; the planting information comprises any one or more of row spacing, plant spacing, planting area or planting density. The invention provides a tobacco field planting information extraction method based on unmanned aerial vehicle remote sensing images, and aims to solve the problems that in the prior art, a crop area acquisition technology depending on satellite remote sensing data is difficult to be suitable for mountain tobacco planting, and tobacco planting information of a mountain area still needs to depend on manual field investigation. The purposes of accurately obtaining tobacco planting information of a mountain area by using an unmanned aerial vehicle remote sensing technology and improving the modernization degree of tobacco agriculture are achieved.