摘要
针对当前的光学遥感图像舰船检测算法无法适用于不同复杂背景的问题,根据人造目标和自然景物的亮度、颜色、边缘特征,提出了基于区域协方差特征值的显著性检测方法,讨论了单一特征值对图像显著性做出的贡献,并使用图像信息熵来度量显著图的有效性。在没有后续虚警目标剔除过程的前提下,对云、雾、海杂波、存在岛屿等复杂背景下的舰船进行检测试验,结果表明:算法能够成功检测出舰船目标,有效抑制虚警,而且本文算法简单高效,适合于工程应用。对获得的包含舰船目标的光学遥感图像进行了试验测试,表明在AUC评价指标上也优于其他5种典型显著性算法。
Because the most existing ship detection methods do not perform well for various high sea clutter situations,according to the characteristic difference between man‐made object and natural background,we propose a novel saliency detection model by computing the eigenvalues of region covariances. To the best of our knowledge,there is no existing reference in the literature about exploring the relationship between the different eigenvalues of region covariances and saliency so far. We further integrate the feature maps linearly by assigning adaptive weight value based on information entropy. The proposed approach has a remarkable ability to pop out targets and suppress distractors against clutter introduced by heavy clouds,islands as well as ship wakes. Furthermore,our model is fast and efficient which has great potential in engineering applications. Extensive experiments have been carried out on optical satellite images and experimental results demonstrate that our approach outperforms 5 existing salient object detection methods in the Area Under the Receiver Operating Characteristics.
引文
[1]王彦情,马雷,田原.光学遥感图像舰船目标检测与识别综述[J].自动化学报,2011,37(9):10291039.Wang Yanqing,Ma Lei,Tian Yuan.Stateoftheart of ship detection and recognition in optical remotely sensed imagery[J].Acta Automatica Sinica,2011,37(9):10291039.
[2]刘峰,沈同圣,马新星,等.基于多波段深度神经网络的舰船目标识别[J].光学精密工程,2017,25(11):29392946.Liu Feng,Shen Tongsheng,Ma Xinxing,et al.Ship recongnition based on multiband deep neural network[J].Optics and Precision Engineering,2017,25(11):29392946.
[3]Tang Jiexiong,Deng Chenwei,Huang Guangbin,et al.Compresseddomain ship detection on spaceborne optical image using deep neural network and extreme learning machine[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(3):11741185.
[4]Bi F H,Zhu B C,Gao L M,et al.A visual search inspired computational model for ship detection in optical satellite images[J].IEEE Geoscience and Remote Sensing Letters,2012,9(4):749753.
[5]张国敏,殷建平,祝恩,等.遥感图像中基于视觉显著性的分层目标检测[J].吉林大学学报:工学版,2007,37(3):625629.Zhang Guomin,Yin Jianping,Zhu En,et al.Hierarchical object detection in remote sensing image based on vision saliency[J].Journal of Jilin University(Engineering and Technology Edition),2007,37(3):625629.
[6]徐芳,刘晶红,曾冬冬,等.基于视觉显著性的无监督海面舰船检测与识别[J].光学精密工程,2017,25(5):13001311.Xu Fang,Liu Jinghong,Zeng Dongdong,et al.Detection and identification of unsupervised ships and warships on sea surface based on visual saliency[J].Optics and Precision Engineering,2017,25(5):13001311.
[7]Itti L,Koch C,Niebur E.A model of saliencybased visual attention for rapid scene analysis[J].IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(11):12541259
[8]Harel J,Koch C,Perona P.Graphbased visual saliency[J].Advances in Neural Information Processing Systems,2006,19:545552.
[9]张文杰,熊庆宇.基于对比度与空间位置特征的显著性区域检测[J].吉林大学学报:工学版,2015,45(5):17101716.Zhang Wenjie,Xiong Qingyu.Image salient region detection algorithm based on contrast and spatial location[J].Journal of Jilin University(Engineering and Technology Edition),2015,45(5):17101716.
[10]Shu F,Li J,Tian Y H,et al.Learning discriminative subspaces on random contrasts for image saliency analysis[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(5):10951108.
[11]Erdem E,Erdem A.Visual saliency estimation by nonlinearly integrating features using region covariances[J].Journal of Vision,2013,13(4):119.
[12]Hou X D,Zhang L Q.Saliency detection:a spectral residual approach[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Los Alamitos:IEEE Computer Society Press,2007:18.
[13]Tuzel O,Porikli F,Meer P.Region covariance:a fast descriptor for detection and classification[C]∥The9th European Conference on Computer Vision,Graz,Austria,2006,3952:589600.
[14]Cao Z J,Ge Y C,Feng J L.Fast target detection method for highresolution SAR images based on variance weighted information entropy[J].Eurasip Journal on Advances in Signal Processing,2014,45:111.
[15]Cheng G,Han J W.A survey on object detection in optical remote sensing images[J].ISPRS Journal of Photogrammetry and Remote Sensing,2016,117:1128.
[16]Wang Y H,Liu H W.A hierarchical ship detection scheme for highresolution SAR images[J].IEEETransactions on Geoscience and Remote Sensing,2012,50(10):41734184.
[17]Forstner W,Moonen B.A Metric for Covariance Matrices[M].Heidelberg:Springer,2003:299309.
[18]Qin Y,Lu H C,Xu Y Q,et al.Saliency detection via cellular automata[C]∥Proceedings of the IEEEConference on Computer Vision and Pattern Recognition,Boston,USA,2015:110119.