Ship Detection Based on Deep Convolutional Neural Networks for Polsar Images
Ship Detection Based on Deep Convolutional Neural Networks for Polsar Images
复制标题
DOI：
10.1109/igarss.2018.8518589
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Feng Zhou;Weiwei Fan;Qiangqiang Sheng;Mingliang Tao
中科院分区：
文献类型：
--
作者：
Feng Zhou;Weiwei Fan;Qiangqiang Sheng;Mingliang Tao
本文提出了一种基于深度卷积神经网络的PolSAR图像舰船检测方法。该方法首先利用固定大小的滑动窗口将PolSAR图像分割成多个子样本，有效地提取平移不变的空间特征。在此基础上，利用改进的基于快速区域卷积神经网络(FASTER-RCNN)方法实现了对不同大小船舶的检测，并对检测结果进行了融合。最后，用实际测量的NASAlJPL AIRSAR数据集对该方法进行了验证，并与改进的恒虚警率(CFAR)检测器进行了性能比较。实验结果验证了该检测算法的有效性和通用性。
In this paper, we proposed a ship detection method based on deep convolutional neural networks for PolSAR images. The proposed ship detector firstly segments PolSAR images into sub-samples using a sliding window of fixed size to effectively extract translational-invariant spatial features. Further, the modified faster region based convolutional neural network (Faster-RCNN) method is utilized to realize ship detection for ships with different sizes and fusion the detection result. Finally, the proposed method was validated using real measured NASAlJPL AIRSAR datasets by comparing the performance with the modified constant false alarm rate (CFAR) detector. The comparison results demonstrate the validity and generality of the proposed detection algorithm.