Remote sensing image small target detection method based on four-scale deep and shallow layer feature fusion

Abstract

The invention provides a remote sensing image small target detection method based on four-scale deep and shallow layer feature fusion. The method comprises the following steps: constructing a remote sensing image small target detection network structure based on four-scale deep and shallow layer feature fusion; training the network structure by adopting transfer learning to obtain a trained network structure; inputting a remote sensing data set into the trained network structure to obtain a target detection result of the remote sensing image: in the training process of the network structure, performing feature extraction on each layer of the input image by adopting VGG16, and fusing the extracted features of each layer by utilizing a feature fusion module to obtain four output feature layers; and inputting the output feature layer to a detection layer, and training the network structure by using an improved loss function to obtain a trained network. The method provided by the inventionhas the beneficial effects that the small target detection capability, speed, robustness and accuracy of the high-resolution remote sensing image are improved.

Description

technical field [0001] The invention relates to the field of remote sensing image processing, in particular to a method for detecting small targets in remote sensing images based on four-scale deep and shallow layer feature fusion. Background technique [0002] Small target detection in remote sensing images is one of the research hotspots in the field of remote sensing. The development of high spatial resolution (High SpatialResolution, HSR) remote sensing image sensor has accelerated the acquisition of various remote sensing images, such as aerial and satellite images with sufficient detailed spatial structure information. These remote sensing images can facilitate a wide range of military and civilian applications, such as ocean monitoring, urban detection, cargo transportation, port management, etc. Different from obtaining ground natural images from the horizontal direction, obtaining high spatial resolution remote sensing images needs to be viewed from a top-down pers...

AI Technical Summary

Problems solved by technology

[0005] In view of the fact that the existing small targets occupy less image pixels in high-resolution remote sensing images, the information contained in the characteristic information is not obvious, and there are often missed and false detections in the detection, which

Images