Bi Fukun, Hou Jinyuan, Chen Liang, Yang Zhihua, Wang Yanping
School of Information Science and Technology, North China University of Technology, Beijing 100144, China.
School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China.
Sensors (Basel). 2019 May 16;19(10):2271. doi: 10.3390/s19102271.
Ship detection plays a significant role in military and civil fields. Although some state-of-the-art detection methods, based on convolutional neural networks (CNN) have certain advantages, they still cannot solve the challenge well, including the large size of images, complex scene structure, a large amount of false alarm interference, and inshore ships. This paper proposes a ship detection method from optical remote sensing images, based on visual attention enhanced network. To effectively reduce false alarm in non-ship area and improve the detection efficiency from remote sensing images, we developed a light-weight local candidate scene network( L 2 CSN) to extract the local candidate scenes with ships. Then, for the selected local candidate scenes, we propose a ship detection method, based on the visual attention DSOD(VA-DSOD). Here, to enhance the detection performance and positioning accuracy of inshore ships, we both extract semantic features, based on DSOD and embed a visual attention enhanced network in DSOD to extract the visual features. We test the detection method on a large number of typical remote sensing datasets, which consist of Google Earth images and GaoFen-2 images. We regard the state-of-the-art method [sliding window DSOD (SW+DSOD)] as a baseline, which achieves the average precision (AP) of 82.33%. The AP of the proposed method increases by 7.53%. The detection and location performance of our proposed method outperforms the baseline in complex remote sensing scenes.
舰船检测在军事和民用领域都发挥着重要作用。尽管一些基于卷积神经网络(CNN)的先进检测方法具有一定优势,但它们仍无法很好地应对挑战,包括图像尺寸大、场景结构复杂、大量虚警干扰以及近岸舰船等问题。本文提出了一种基于视觉注意力增强网络的光学遥感图像舰船检测方法。为有效减少非舰船区域的虚警并提高遥感图像的检测效率,我们开发了一种轻量级局部候选场景网络(L2CSN)来提取含有舰船的局部候选场景。然后,对于选定的局部候选场景,我们提出了一种基于视觉注意力DSOD(VA-DSOD)的舰船检测方法。在此,为提高近岸舰船的检测性能和定位精度,我们既基于DSOD提取语义特征,又在DSOD中嵌入视觉注意力增强网络来提取视觉特征。我们在大量由谷歌地球图像和高分二号图像组成的典型遥感数据集上测试了该检测方法。我们将先进方法[滑动窗口DSOD(SW+DSOD)]作为基线,其平均精度(AP)为82.33%。所提方法的AP提高了7.53%。在复杂遥感场景中,我们所提方法的检测和定位性能优于基线。