Wind driven generator deep learning detection result optimization method and system

The invention relates to the technical field of remote sensing image classification and target detection, discloses a method and a system for optimizing a deep learning detection result of a wind driven generator, and aims to solve the problem that the accuracy rate and the recall rate are difficult to obtain at the same time in the prior art. Establishing a deep residual network RESET34 skeleton model, and completing preliminary detection on a test image at the same time; target object attributes are defined, distribution characteristics of target objects are defined, events of fan distribution characteristics are constructed, and the conditional probability of the events is estimated through a statistical method; a Bayesian formula is adopted to calculate and obtain a final confidence coefficient; and extracting the detection object with the original confidence and the final confidence greater than or equal to a threshold value, and calculating a detection precision index to obtain a final evaluation result