基于结构化稀疏表达的高分辨率光学遥感图像的船只检测
|
摘要
为克服近岸船只检测中复杂港内背景干扰和基于深度学习算法的大视场光学遥感图像标注工作量大的困难,本文提出了基于小样本集的结构化稀疏表达方法来实现近岸船只检测的算法。构建由近岸船只目标,背景干扰信息和误差矩阵等三部分子字典组成的结构化稀疏表达字典,经小样本集的字典训练过程生成判别性稀疏编码。首先将多方向近岸船只目标样本与港内复杂背景信息样本经过HOG特征提取和PCA分析对原子进行初始化,然后使用K-SVD和LASSO算法对字典进行训练。在字典中引入误差矩阵对样本的类内差异进行表示,增强了稀疏编码的判别能力和系统鲁棒性。最后提出船只目标区域提取的置信度计算方法,对生成的结构化稀疏编码进行判别,提取船只目标区域,实现船只检测。通过对不同尺寸字典模型、引入误差矩阵前后的结构化稀疏表达模型进行实验,实验结果表明提出的引入误差矩阵的结构化稀疏表达方法的有效性,以及在小样本集下比现有技术方法具有更好的检测性能。
In order to overcome the harbor background interference and prevent a huge number of annotations from large view optical remote sensing images, this paper proposed a structured sparse representation method based on small sample set to realize the inshore ship detection. Here, the constructed structured sparse representation dictionary contained three parts which include inshore ship sub-dictionary part, harbor background sub-dictionary part and error matrix part. By iterated structured sparse representation dictionary training process, discriminative sparse coding can be generated for inshore ship detection according to ship confident value calculation. First, the multi-directional near-shore vessel target sample and the complex background information samples were subjected to HOG feature extraction and PCA analysis to initialize the atom. Then the dictionary was trained by K-SVD and LASSO algorithm. Then The error matrix was introduced into the dictionary to represent the intra-class difference of the sample, which enhances the discriminative ability and system robustness of sparse coding. Finally, the confidence calculation method for ship target area extraction was proposed, and the generated structured sparse coding was analyzed to realize the rapid inshore ship extraction. Experiments were carried out on different sizes dictionary models and structured sparse expression models before and after the introduction of error matrices. The experiment results had been demonstrated that it can provide a discriminative sparse codes for inshore ship detection to achieve better performance than state of the art methods.
In order to overcome the harbor background interference and prevent a huge number of annotations from large view optical remote sensing images, this paper proposed a structured sparse representation method based on small sample set to realize the inshore ship detection. Here, the constructed structured sparse representation dictionary contained three parts which include inshore ship sub-dictionary part, harbor background sub-dictionary part and error matrix part. By iterated structured sparse representation dictionary training process, discriminative sparse coding can be generated for inshore ship detection according to ship confident value calculation. First, the multi-directional near-shore vessel target sample and the complex background information samples were subjected to HOG feature extraction and PCA analysis to initialize the atom. Then the dictionary was trained by K-SVD and LASSO algorithm. Then The error matrix was introduced into the dictionary to represent the intra-class difference of the sample, which enhances the discriminative ability and system robustness of sparse coding. Finally, the confidence calculation method for ship target area extraction was proposed, and the generated structured sparse coding was analyzed to realize the rapid inshore ship extraction. Experiments were carried out on different sizes dictionary models and structured sparse expression models before and after the introduction of error matrices. The experiment results had been demonstrated that it can provide a discriminative sparse codes for inshore ship detection to achieve better performance than state of the art methods.
引文
[1] Greidanus H,Kourti N.A Detailed Comparison between Radar and Optical Vessel Signatures[C]//IEEE International Conference on Geoscience and Remote Sensing Symposium.IEEE,2007:3267-3270.
[2] 张风丽,张磊,吴炳方.欧盟船舶遥感探测技术与系统研究的进展[J].遥感学报,2007,11(4):552-562.Zhang F L,Zhang L,Wu B F.Progress of Ship Detection Technology and System Based on Remote Sensing Technology in European Union[J].Journal of Remote Sensing,2007,11(4):552-562.(in Chinese)
[3] Liu G,Zhang Y,Zheng X,et al.A New Method on Inshore Ship Detection in High-Resolution Satellite Images Using Shape and Context Information[J].IEEE Geoscience & Remote Sensing Letters,2013,11(3):617- 621.
[4] Bi F,Jing C,Yin Z,et al.A Decision Mixture Model-Based Method for Inshore Ship Detection Using High-Resolution Remote Sensing Images[J].Sensors,2017,17(7):1470.
[5] He H,Lin Y,Fan C,et al.Inshore Ship Detection in Remote Sensing Images via Weighted Pose Voting[J].IEEE Transactions on Geoscience & Remote Sensing,2017,PP(99):1-17.
[6] Zou Z,Shi Z.Ship Detection in Spaceborne Optical Image With SVD Networks[J].IEEE Transactions on Geoscience & Remote Sensing,2016,54(10):5832-5845.
[7] Lin H,Shi Z,Zou Z.Fully Convolutional Network With Task Partitioning for Inshore Ship Detection in Optical Remote Sensing Images[J].IEEE Geoscience and Remote Sensing Letters,2017,PP(99):1-5.
[8] 吴金亮,王港,梁硕,等.基于Mask R-CNN的舰船目标检测研究[J].无线电工程,2018,48(11):947-952.Wu J L,Wang G,Liang S,et al.Ship Object Detection Based on Mask R-CNN[J].Radio Engineering,2018,48(11):947-952.(in Chinese)
[9] 张磊,洪星,王岳环,等.高分辨率遥感图像投影分析的靠岸舰船检测[J].中国图象图形学报,2018,23(9):1424-1432.Zhang L,Hong X,Wang Y H,et al.Inshore ship detection in high-resolution remote sensing image using projection nanlysis[J].Journal of Image and Graphics,2018,23(9):1424-1432.(in Chinese)
[10] 王慧利,朱明,蔺春波,等.光学遥感图像中复杂海背景下的舰船检测[J].光学精密工程,2018,26(3):723-732.Wang H L,Zhu M,Lin C B,et al.Ship Detection of Complex Sea Background in Optical Remote Sensing Images[J].Optics and Precision Engineering,2018,26(3):723-732.(in Chinese)
[11] Luo W,Wang W,Lang F,et al.Ship Detection of Remote Sensing Image on FRHT and Multi-Points Curvature Based Polygon Approximation[J].Research Journal of Applied Sciences Engineering & Technology,2012,4(15):2590-2599
[12] Yokoya N,Iwasaki A.Object Detection Based on Sparse Representation and Hough Voting for Optical Remote Sensing Imagery[J].IEEE Journal of Selected Topics In Applied Earth Observations and Remote Sensing,2015,8(5):2053-2062.
[13] Li H,Li Z,Chen Z,et al.Multi-layer sparse coding model-based ship detection for optical remote-sensing images[J].International Journal of Remote Sensing,2017,38(22):6281- 6297.
[14] Greidanus H,Kourti N.A Detailed Comparison between Radar and Optical Vessel Signatures[C]//IEEE International Conference on Geoscience & Remote Sensing Symposium.IEEE,2007.
[15] Dalal N,Triggs B.Histograms of Oriented Gradients for Human Detection[C]//IEEE Computer Society Conference on Computer Vision & Pattern Recognition.IEEE Computer Society,2005:886- 893.
[16] Mika S,Smola A,Scholz M.Kernel PCA and de-noising in feature spaces[C]//Conference on Advances In Neural Information Processing Systems II.MIT Press,1999:536-542.
[17] Aharon M,Elad M,Bruckstein A.-SVD:An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311- 4322.
[18] Tropp J A,Gilbert A C.Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit[J].IEEE Transactions on Information Theory,2007,53(12):4655- 4666.
[19] Rosenfeld A,Vanderbrug G J.Coarse-Fine Template Matching[J].IEEE Transactions on Systems Man & Cybernetics,1977,7(2):104-107.
[20] Morioka N,Satoh S.Generalized Lasso based Approximation of Sparse Coding for Visual Recognition[J].Advances In Neural Information Processing Systems,2012,26(1):181-189.
[21] Mairal J,Bach F,Ponce J.Task-Driven Dictionary Learning[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2012,34(4):791- 804.
[2] 张风丽,张磊,吴炳方.欧盟船舶遥感探测技术与系统研究的进展[J].遥感学报,2007,11(4):552-562.Zhang F L,Zhang L,Wu B F.Progress of Ship Detection Technology and System Based on Remote Sensing Technology in European Union[J].Journal of Remote Sensing,2007,11(4):552-562.(in Chinese)
[3] Liu G,Zhang Y,Zheng X,et al.A New Method on Inshore Ship Detection in High-Resolution Satellite Images Using Shape and Context Information[J].IEEE Geoscience & Remote Sensing Letters,2013,11(3):617- 621.
[4] Bi F,Jing C,Yin Z,et al.A Decision Mixture Model-Based Method for Inshore Ship Detection Using High-Resolution Remote Sensing Images[J].Sensors,2017,17(7):1470.
[5] He H,Lin Y,Fan C,et al.Inshore Ship Detection in Remote Sensing Images via Weighted Pose Voting[J].IEEE Transactions on Geoscience & Remote Sensing,2017,PP(99):1-17.
[6] Zou Z,Shi Z.Ship Detection in Spaceborne Optical Image With SVD Networks[J].IEEE Transactions on Geoscience & Remote Sensing,2016,54(10):5832-5845.
[7] Lin H,Shi Z,Zou Z.Fully Convolutional Network With Task Partitioning for Inshore Ship Detection in Optical Remote Sensing Images[J].IEEE Geoscience and Remote Sensing Letters,2017,PP(99):1-5.
[8] 吴金亮,王港,梁硕,等.基于Mask R-CNN的舰船目标检测研究[J].无线电工程,2018,48(11):947-952.Wu J L,Wang G,Liang S,et al.Ship Object Detection Based on Mask R-CNN[J].Radio Engineering,2018,48(11):947-952.(in Chinese)
[9] 张磊,洪星,王岳环,等.高分辨率遥感图像投影分析的靠岸舰船检测[J].中国图象图形学报,2018,23(9):1424-1432.Zhang L,Hong X,Wang Y H,et al.Inshore ship detection in high-resolution remote sensing image using projection nanlysis[J].Journal of Image and Graphics,2018,23(9):1424-1432.(in Chinese)
[10] 王慧利,朱明,蔺春波,等.光学遥感图像中复杂海背景下的舰船检测[J].光学精密工程,2018,26(3):723-732.Wang H L,Zhu M,Lin C B,et al.Ship Detection of Complex Sea Background in Optical Remote Sensing Images[J].Optics and Precision Engineering,2018,26(3):723-732.(in Chinese)
[11] Luo W,Wang W,Lang F,et al.Ship Detection of Remote Sensing Image on FRHT and Multi-Points Curvature Based Polygon Approximation[J].Research Journal of Applied Sciences Engineering & Technology,2012,4(15):2590-2599
[12] Yokoya N,Iwasaki A.Object Detection Based on Sparse Representation and Hough Voting for Optical Remote Sensing Imagery[J].IEEE Journal of Selected Topics In Applied Earth Observations and Remote Sensing,2015,8(5):2053-2062.
[13] Li H,Li Z,Chen Z,et al.Multi-layer sparse coding model-based ship detection for optical remote-sensing images[J].International Journal of Remote Sensing,2017,38(22):6281- 6297.
[14] Greidanus H,Kourti N.A Detailed Comparison between Radar and Optical Vessel Signatures[C]//IEEE International Conference on Geoscience & Remote Sensing Symposium.IEEE,2007.
[15] Dalal N,Triggs B.Histograms of Oriented Gradients for Human Detection[C]//IEEE Computer Society Conference on Computer Vision & Pattern Recognition.IEEE Computer Society,2005:886- 893.
[16] Mika S,Smola A,Scholz M.Kernel PCA and de-noising in feature spaces[C]//Conference on Advances In Neural Information Processing Systems II.MIT Press,1999:536-542.
[17] Aharon M,Elad M,Bruckstein A.-SVD:An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311- 4322.
[18] Tropp J A,Gilbert A C.Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit[J].IEEE Transactions on Information Theory,2007,53(12):4655- 4666.
[19] Rosenfeld A,Vanderbrug G J.Coarse-Fine Template Matching[J].IEEE Transactions on Systems Man & Cybernetics,1977,7(2):104-107.
[20] Morioka N,Satoh S.Generalized Lasso based Approximation of Sparse Coding for Visual Recognition[J].Advances In Neural Information Processing Systems,2012,26(1):181-189.
[21] Mairal J,Bach F,Ponce J.Task-Driven Dictionary Learning[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2012,34(4):791- 804.