A target detection algorithm based on feature enhancement and dense scene optimization is proposed

aiming at the problem of missed detection and error detection in remote sensing image target detection. By optimizing the Faster R-CNN framework and adding feature-enhanced convolutional layers to make the small target features more significant

the improved non-maximum suppression algorithm is used to update the target confidence of dense scenes

thus improving the target detection performance of remote sensing images. The experimental results show that the proposed algorithm improves the target detection precision

compared with the existing methods in the DOTA remote sensing dataset.