Remote sensing image target detection method

The invention discloses a remote sensing image target detection method, which comprises the steps of collecting a remote sensing image data set, labeling the data set, making a remote sensing image data set in a YOLO format, and dividing the remote sensing image data set into a training set and a test set; a multi-scale neural network based on an enhanced receptive field is established, the multi-scale neural network is mainly composed of an input port, a backbone network, a neck network and a detection head, and the backbone network and the neck network form a main module of the multi-scale neural network for enhancing small target features; inputting the remote sensing image of the training set into a receptive field enhanced multi-scale neural network for training and verification to obtain an optimal detection model; and performing target detection on the test set by using the trained and verified optimal model. The invention provides a multi-scale remote sensing image target detection method for enhancin