自适应旋转区域生成网络的遥感图像舰船目标检测

Ship Object Detection of Remote Sensing Images Based on Adaptive Rotation Region Proposal Network

针对遥感图像中舰船形状狭长、分布杂乱等特性导致检测难度增大的问题,提出了一种基于快速区域卷积神经网络(Faster R-CNN)的舰船目标检测方法。采用双路网络提取舰船目标特征,为了使特征图充分融合底层细节信息和高层语义信息,用多尺度融合特征金字塔网络(MFPN)进行特征融合;在候选框生成阶段,提出了自适应旋转区域生成网络(AR-RPN),集中在目标中心位置生成旋转锚框,以高效获取优质的候选框。为了提升网络对舰船目标的检测率,结合改进的损失函数对网络进行优化。在HRSC2016和DOTA舰船数据集上的测试结果表明,本方法的平均精度分别为89.10%和88.64%,能很好地适应遥感图像中舰船的形状与分布特性。

Aiming at the problem that increased difficulties in detection of ship detection in remote sensing images caused by the narrow and long shape,disorderly distribution and other characteristics,a ship target detection method based on faster region-convolution neural network(Faster R-CNN)is proposed in this paper.The method uses a two-way network to extract ship target features.In order to make the feature map fully integrate the lowlevel detail information and high-level semantic information,a multi-scale fusion feature pyramid network(MFPN)is used for feature fusion;in the candidate frame generation stage,an adaptive rotation region proposal network(AR-RPN)is proposed to generate a rotating anchor frame at the center of the target to efficiently obtain highquality candidate frames.In order to improve the detection rate of the network to ship targets,the network is optimized with an improved loss function.The test results on the public ship data sets HRSC2016 and the DOTA show that the average accuracy of this method is 89.10% and 88.64%,respectively,which can well adapt to the shape and distribution characteristics of ships in remote sensing images.