基于Transformer的遥感图像目标检测算法研究

Research on Remote Sensing Image Target Detection Algorithm Based on Transformer

针对遥感图像中目标特征不明显等导致的精度低、性能差问题。我们给出基于改进Transformer的遥感图像目标检测模型。首先,运用迁移学习加载模型,并且用ResNet101替换原始主干;其次在特征提取阶段,在主干网的bottlenet层中引入SE注意力机制;最后,将原有损失函数优化为L1损失和CIOU损失的结合。实验结果证实,改进之后的模型相对于基准而言,在精度和性能上都有一定的提高。

Aiming at the problem of low accuracy and poor performance caused by unobvious target features in remote sensing images, we give a remote sensing image target detection model based on improved Transformer. Firstly, transfer learning is used to load the model, and ResNet101 is used to replace the original trunk. Secondly, in the feature extraction stage, the SE attention mechanism is introduced into the bottlenet layer of the backbone network;finally, the original loss function is optimized to a combination of L1 loss and CIOU loss. The experimental results show that the improved model has a certain improvement in accuracy and performance compared with the benchmark.