基于深度学习的复杂气象条件下海上船只检测

被引:11
作者
熊咏平 [1 ,2 ]
丁胜 [1 ,2 ]
邓春华 [1 ,2 ]
方国康 [1 ,2 ]
龚锐 [1 ,2 ]
机构
[1] 武汉科技大学计算机科学与技术学院
[2] 智能信息处理与实时工业系统湖北省重点实验室
关键词
YOLO v2; 目标检测; 多尺度目标检测; 显著性分割;
D O I
暂无
中图分类号
TP18 [人工智能理论]; TP751 [图像处理方法];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ; 081002 ;
摘要
为了解决复杂海情环境下的不同种类和大小的舰船检测问题,提出一种实时的深度学习的目标检测算法。首先,提出了一种清晰图片和模糊图片(雨、雾等图片)判别的方法;然后,在YOLO v2的深度学习框架的基础上提出一种多尺度目标检测算法;最后,针对遥感图像舰船目标的特点,提出了一种改进的非极大值抑制和显著性分割算法,对最终的检测结果进一步优化。在复杂海情和气象条件下的舰船目标公开比赛的数据集上,实验结果表明,相比原始的YOLO v2,该方法的准确率提升了16%。
引用
收藏
页码:3631 / 3637
页数:7
相关论文
共 20 条
[11]  
YOLOv3:an incremental improvement. REDMON J,FARHADI A. http://cn.arxiv.org/pdf/1804.02767 . 2018
[12]  
An Improved Otsu Threshold Segmentation Method for Underwater Simultaneous Localization and Mapping-Based Navigation. Yuan,Martinez,Eckert,et al. Sensors . 2016
[13]  
Region-based convolutional networks for accurate object detection and segmentation. Girshick R,Donahue J,Darrell T, et al. Pattern Analysis and Machine Intelligence, IEEE Transactions on . 2016
[14]  
Weakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detection. ZHANG F,DU B,ZHANG L,et al. IEEE Transactions on Geoscience and Remote Sensing . 2016
[15]  
An extended set of haar-like features for rapid object detection. Lienhart R,Maydt J. Proc.of the IEEE International Conference on Image Processing . 2002
[16]  
Synthetic Aperture Radar Signal Processing. SOUMEKH M. . 1999
[17]  
Saliency detection:A spectral residual approach. Hou X,Zhang L. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 2007
[18]  
Context-Aware Saliency Detection. Stas Goferman,Lihi Zelnik-Manor,Ayellet Tal. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2012
[19]  
Support Vector Machines. Hearst M A,Dumais S T,Osman E,et al. IEEE Intelligent Systems . 1998
[20]  
Histograms of oriented gradients for human detection. Dalal N,Triggs B. 2005 IEEE Conference on Computer Vision and Pattern Recognition . 2005