Due to real-world constraints,the quantity of ship datasets derived from remote sensing data is sub-stantially limited and can't fulfill the extensive sample demands required for training deep learning algorithms. According to this problem,a high-quality synthesizing method for three-band optical high-resolution remote sensing images containing ship targets is introduced,which utilizes 3D models and generative adversarial networks with style transfer capabilities. Based on the constructed dataset,synthetic samples are generated and evaluated. The expe-riments indicate that the approach can synthesize images visually close to real images. Incorporating these syn-thetic samples into the training process of detection models results in an increase of 2.6％ in mAP for Faster R-CNN and 2.3％ for YOLOv5.
维普
万方数据