Aircraft target detection in remote sensing images based on improved YOLOv7
Aiming at the problems of low detection accuracy and loss of small target features caused by the complex back-ground of remote sensing images,an aircraft target detection algorithm for remote sensing images with improved YOLOv7 is pro-posed.The algorithm adopts the strategy of migration learning to fine-tune the pre-trained model,which improves the generalization ability of the model;and acquires the contextual semantic information by introducing the Convolutional Block Attention Module(CBAM)in the detection head of the model,in order to enhance the feature extraction ability of the occluders and small targets.The RSOD dataset is used to verify the effect of the improved algorithm,and the results show that the mAP of the improved YOLOv7 algorithm reaches 97.13%,which is 3.08 percentage piont higher than that of the original YOLOv7,and effectively improves the detection accuracy of the aircraft in remote sensing images.
万方数据
