【摘要】 针对复杂背景SAR图像船舶目标检测易受地物干扰影响,导致模型检测率低的问题,提出将结合通道和空间的双注意力机制CBAM引入目标检测网络;将膨胀卷积和concat特征融合技术应用于目标检测网络中提升模型对小尺寸目标的鲁棒性;为了进一步提高模型的检测速度,使用轻量级MobileNet作为基础特征提取网络;同时采用一个新的二分类损失函数使模型训练能够对难易样本设置不同的权重。最后,通过在构建的复杂背景SAR图像船舶目标检测数据集SDATA上进行实验,实验结果表明该算法在复杂背景SAR船舶目标检测中其平均检测精度与综合评价指标F1-score值分别为88.9%和91.2%,检测速度达42.1 fps,从而验证了该模型不仅能够有效提升复杂背景SAR图像船舶目标的检测精度,而且在一定程度上提高了目标的检测速度。更多还原

【Abstract】 Aiming at the problem that ship detection in complex background SAR images is easily affected by ground objects, which leads to low detection rate of model, we propose to introduce CBAM,which combines channel and space mechanism, into target detection network. The expansion convolution and concatenation feature fusion technology are applied to the target detection network to improve the robustness of model to small targets. In order to further improve the detection speed of model, the lightweight MobileNet is used, and a new two class loss function is used to make the model training set different weights for difficult and easy samples. Finally, experiments are carried out on SDATA,a ship target detection data set with complex background SAR images. It is showed that the mean average precision and comprehensive evaluation index F1-score of the proposed algorithm are 88.9% and 91.2% respectively, and the detection speed is 42.1 fps. It is verified that the proposed model can not only effectively improve the detection accuracy of ship targets in SAR images with complex background, but also improve the detection speed to a certain extent.更多还原