基于注意力及生成对抗网络的遥感影像目标检测

针对传统目标检测算法在环境多变、背景复杂、目标聚集、小目标过多的航空遥感影像目标检测上效果不理想的问题, 本文提出了一种基于注意力机制及生成对抗网络的遥感影像目标检测模型Attention-GAN-Mask R-CNN. 该模型将注意力、生成对抗网络和Mask R-CNN结合起来, 用以解决遥感影像目标检测中存在的问题. 实验结果表明, 在复杂的遥感影像数据集中, 该方法提升了目标检测的效率和准确率.

Object Detection in Remote Sensing Image Based on Attention Mechanism and GAN

The traditional object detection algorithm is subject to changeable environment, complex background, target aggregation and too many small targets, showing disadvantages in the detection of aerial remote sensing images. This study presents the Attention-GAN-Mask R-CNN model for the object detection in remote sensing image based on attention mechanism and generative adversarial network (GAN). This model combines attention, generative adversarial network and Mask R-CNN to solve the above problems. The experimental results show that this method can improve the efficiency and accuracy of target detection in the complex remote sensing images.