Method and equipment for detecting defects of power transmission line by unmanned aerial vehicle, and storage medium

The invention discloses a method for detecting defects of a power transmission line by an unmanned aerial vehicle. The method comprises the following steps: S1, setting a data set for training a detection neural network; s2, training the detection neural network according to the data set, and outputting a detection result after training is completed; and S3, setting a detection standard to evaluate a detection result output by the detection neural network, and evaluating the performance of the detection neural network. According to the set data set, the image covering multiple scenes, multiple semantics and multiple significant features is selected, and the detection neural network is trained, so that the trained detection neural network has relatively high accuracy; and evaluating a detection result of the detection neural network. Whether the detection of the neural network on the data set is accurate or not is judged, and the performance of the neural network is evaluated and detected. And the detection ac