The spaceborne synthetic aperture radar(SAR)sparse flight 3-D imaging technology through multiple observations of the cross-track direction is designed to form the cross-track equivalent aperture,and achieve the third...The spaceborne synthetic aperture radar(SAR)sparse flight 3-D imaging technology through multiple observations of the cross-track direction is designed to form the cross-track equivalent aperture,and achieve the third dimensionality recognition.In this paper,combined with the actual triple star orbits,a sparse flight spaceborne SAR 3-D imaging method based on the sparse spectrum of interferometry and the principal component analysis(PCA)is presented.Firstly,interferometric processing is utilized to reach an effective sparse representation of radar images in the frequency domain.Secondly,as a method with simple principle and fast calculation,the PCA is introduced to extract the main features of the image spectrum according to its principal characteristics.Finally,the 3-D image can be obtained by inverse transformation of the reconstructed spectrum by the PCA.The simulation results of 4.84 km equivalent cross-track aperture and corresponding 1.78 m cross-track resolution verify the effective suppression of this method on high-frequency sidelobe noise introduced by sparse flight with a sparsity of 49%and random noise introduced by the receiver.Meanwhile,due to the influence of orbit distribution of the actual triple star orbits,the simulation results of the sparse flight with the 7-bit Barker code orbits are given as a comparison and reference to illuminate the significance of orbit distribution for this reconstruction results.This method has prospects for sparse flight 3-D imaging in high latitude areas for its short revisit period.展开更多
A novel synthetic aperture radar(SAR)image de-noising method based on the local pixel grouping(LPG)principal component analysis(PCA)and guided filter is proposed.This method contains two steps.In the first step,we pro...A novel synthetic aperture radar(SAR)image de-noising method based on the local pixel grouping(LPG)principal component analysis(PCA)and guided filter is proposed.This method contains two steps.In the first step,we process the noisy image by coarse filters,which can suppress the speckle effectively.The original SAR image is transformed into the additive noise model by logarithmic transform with deviation correction.Then,we use the pixel and its nearest neighbors as a vector to select training samples from the local window by LPG based on the block similar matching.The LPG method ensures that only the similar sample patches are used in the local statistical calculation of PCA transform estimation,so that the local features of the image can be well preserved after coefficients shrinkage in the PCA domain.In the second step,we do the guided filtering which can effectively eliminate small artifacts left over from the coarse filtering.Experimental results of simulated and real SAR images show that the proposed method outstrips the state-of-the-art image de-noising methods in the peak signalto-noise ratio(PSNR),the structural similarity(SSIM)index and the equivalent number of looks(ENLs),and is of perceived image quality.展开更多
针对工业场景下经典迭代最近点(iterative closest point,ICP)算法在点云位姿估计中初始位姿敏感度高、迭代时间长的问题,提出一种基于RGB图像的快速点云配准方法。分别采集RGB图像和点云数据,使用ORB(oriented FAST and rotated BRIEF...针对工业场景下经典迭代最近点(iterative closest point,ICP)算法在点云位姿估计中初始位姿敏感度高、迭代时间长的问题,提出一种基于RGB图像的快速点云配准方法。分别采集RGB图像和点云数据,使用ORB(oriented FAST and rotated BRIEF)算法提取RGB图像特征点,利用Brute-Force算法进行初始匹配,采用随机采样一致性算法优化匹配,得到单应矩阵和旋转平移矩阵,求解汽车零配件初始位姿。进一步采用主成分分析法和双向KD树近邻搜索算法对预处理后的点云数据进行精确配准。实验结果表明,所提算法相较ICP算法,在配准速度和精度上分别提高了87.2%和5.0%,相对于FR-ICP(fast and robust iterative closest point)算法,在配准精度相当的情况下,配准速度提高了55%。展开更多
为了解决张量鲁棒主成分分析(tensor robust principal component analysis,TRPCA)还原低秩结构时同等收缩奇异值造成的信息提取偏差问题,本文考虑区别对待奇异值,使用非凸加权张量Schatten-p范数(0<p<1)分析张量数据,可减少对奇...为了解决张量鲁棒主成分分析(tensor robust principal component analysis,TRPCA)还原低秩结构时同等收缩奇异值造成的信息提取偏差问题,本文考虑区别对待奇异值,使用非凸加权张量Schatten-p范数(0<p<1)分析张量数据,可减少对奇异值的惩罚。为解决数据受损严重难以恢复的问题,提出低秩预分离的方法实现近似低秩部分和近似稀疏部分的预先分离;为增强高阶张量之间相关性同时降低数据对特定噪声的敏感性,提出随机抖动正则器的机制对预分离后成分分别选取随机区域优化,利用噪声信息的随机性来正则化算法得以约束模型的复杂度;最后使用不同类型的图像数据集,包括彩色图像、核磁共振图像、高光谱及多光谱图像和灰度视频,进行高维数据恢复实验。结果表明该方法在图像恢复性能上明显优于其他TRPCA方法,并且在数据受损严重时同样具有优势,有效提取主成分信息的同时减小数据对特定噪声的依赖,具有较强的鲁棒性和适应性,可为TRPCA方法在图像恢复领域中提供参考。展开更多
高光谱图像以其高分辨率的空间和光谱信息在军事、航空航天及民用等遥感领域均有重要应用,具有重要的研究意义。深度学习具有学习能力强、覆盖范围广及可移植性强的优势,成为目前高精度高光谱图像分类技术研究的热点。其中卷积神经网络(...高光谱图像以其高分辨率的空间和光谱信息在军事、航空航天及民用等遥感领域均有重要应用,具有重要的研究意义。深度学习具有学习能力强、覆盖范围广及可移植性强的优势,成为目前高精度高光谱图像分类技术研究的热点。其中卷积神经网络(CNN)因强大的特征提取能力广泛应用于高光谱图像分类方法研究中,取得了有效的研究成果,但该类方法通常单独基于2D-CNN或3D-CNN进行,针对高光谱图像的单一特征,一是不能充分利用高光谱数据本身完整的特征信息;二是虽然相应提取网络局部特征优化性好,但是整体泛化能力不足,在深度挖掘HSI的空间和光谱信息方面存在局限性。鉴于此,提出了基于注意力机制的混合卷积神经网络模型(HybridSN_AM),使用主成分分析法对高光谱图像进行降维,采用卷积神经网络作为分类模型的主体,通过注意力机制筛选出更有区分度的特征,使模型能够提取到更精确、更核心的空间-光谱信息,实现高光谱图像的高精度分类。对Indian Pines(IP)、University of Pavia(UP)和Salinas(SA)三个数据集进行了应用实验,结果表明,基于该模型的目标图像总体分类精度、平均分类精度和Kappa系数均高于98.14%、97.17%、97.87%。与常规HybridSN模型对比表明,HybridSN_AM模型在三个数据集上的分类精度分别提升了0.89%、0.07%和0.73%。有效解决了高光谱图像空间-光谱特征提取与融合的难题,提高HSI分类的精度,具有较强的泛化能力,充分验证了注意力机制结合混合卷积神经网络在高光谱图像分类中的有效性和可行性,对高光谱图像分类技术的发展及应用具有重要的科学价值。展开更多
基金This work was supported by the General Design Department,China Academy of Space Technology(10377).
文摘The spaceborne synthetic aperture radar(SAR)sparse flight 3-D imaging technology through multiple observations of the cross-track direction is designed to form the cross-track equivalent aperture,and achieve the third dimensionality recognition.In this paper,combined with the actual triple star orbits,a sparse flight spaceborne SAR 3-D imaging method based on the sparse spectrum of interferometry and the principal component analysis(PCA)is presented.Firstly,interferometric processing is utilized to reach an effective sparse representation of radar images in the frequency domain.Secondly,as a method with simple principle and fast calculation,the PCA is introduced to extract the main features of the image spectrum according to its principal characteristics.Finally,the 3-D image can be obtained by inverse transformation of the reconstructed spectrum by the PCA.The simulation results of 4.84 km equivalent cross-track aperture and corresponding 1.78 m cross-track resolution verify the effective suppression of this method on high-frequency sidelobe noise introduced by sparse flight with a sparsity of 49%and random noise introduced by the receiver.Meanwhile,due to the influence of orbit distribution of the actual triple star orbits,the simulation results of the sparse flight with the 7-bit Barker code orbits are given as a comparison and reference to illuminate the significance of orbit distribution for this reconstruction results.This method has prospects for sparse flight 3-D imaging in high latitude areas for its short revisit period.
基金supported by the National Natural Science Foundation of China(6200220861572063+1 种基金61603225)the Natural Science Foundation of Shandong Province(ZR2016FQ04)。
文摘A novel synthetic aperture radar(SAR)image de-noising method based on the local pixel grouping(LPG)principal component analysis(PCA)and guided filter is proposed.This method contains two steps.In the first step,we process the noisy image by coarse filters,which can suppress the speckle effectively.The original SAR image is transformed into the additive noise model by logarithmic transform with deviation correction.Then,we use the pixel and its nearest neighbors as a vector to select training samples from the local window by LPG based on the block similar matching.The LPG method ensures that only the similar sample patches are used in the local statistical calculation of PCA transform estimation,so that the local features of the image can be well preserved after coefficients shrinkage in the PCA domain.In the second step,we do the guided filtering which can effectively eliminate small artifacts left over from the coarse filtering.Experimental results of simulated and real SAR images show that the proposed method outstrips the state-of-the-art image de-noising methods in the peak signalto-noise ratio(PSNR),the structural similarity(SSIM)index and the equivalent number of looks(ENLs),and is of perceived image quality.
文摘针对工业场景下经典迭代最近点(iterative closest point,ICP)算法在点云位姿估计中初始位姿敏感度高、迭代时间长的问题,提出一种基于RGB图像的快速点云配准方法。分别采集RGB图像和点云数据,使用ORB(oriented FAST and rotated BRIEF)算法提取RGB图像特征点,利用Brute-Force算法进行初始匹配,采用随机采样一致性算法优化匹配,得到单应矩阵和旋转平移矩阵,求解汽车零配件初始位姿。进一步采用主成分分析法和双向KD树近邻搜索算法对预处理后的点云数据进行精确配准。实验结果表明,所提算法相较ICP算法,在配准速度和精度上分别提高了87.2%和5.0%,相对于FR-ICP(fast and robust iterative closest point)算法,在配准精度相当的情况下,配准速度提高了55%。
文摘为了解决张量鲁棒主成分分析(tensor robust principal component analysis,TRPCA)还原低秩结构时同等收缩奇异值造成的信息提取偏差问题,本文考虑区别对待奇异值,使用非凸加权张量Schatten-p范数(0<p<1)分析张量数据,可减少对奇异值的惩罚。为解决数据受损严重难以恢复的问题,提出低秩预分离的方法实现近似低秩部分和近似稀疏部分的预先分离;为增强高阶张量之间相关性同时降低数据对特定噪声的敏感性,提出随机抖动正则器的机制对预分离后成分分别选取随机区域优化,利用噪声信息的随机性来正则化算法得以约束模型的复杂度;最后使用不同类型的图像数据集,包括彩色图像、核磁共振图像、高光谱及多光谱图像和灰度视频,进行高维数据恢复实验。结果表明该方法在图像恢复性能上明显优于其他TRPCA方法,并且在数据受损严重时同样具有优势,有效提取主成分信息的同时减小数据对特定噪声的依赖,具有较强的鲁棒性和适应性,可为TRPCA方法在图像恢复领域中提供参考。
文摘高光谱图像以其高分辨率的空间和光谱信息在军事、航空航天及民用等遥感领域均有重要应用,具有重要的研究意义。深度学习具有学习能力强、覆盖范围广及可移植性强的优势,成为目前高精度高光谱图像分类技术研究的热点。其中卷积神经网络(CNN)因强大的特征提取能力广泛应用于高光谱图像分类方法研究中,取得了有效的研究成果,但该类方法通常单独基于2D-CNN或3D-CNN进行,针对高光谱图像的单一特征,一是不能充分利用高光谱数据本身完整的特征信息;二是虽然相应提取网络局部特征优化性好,但是整体泛化能力不足,在深度挖掘HSI的空间和光谱信息方面存在局限性。鉴于此,提出了基于注意力机制的混合卷积神经网络模型(HybridSN_AM),使用主成分分析法对高光谱图像进行降维,采用卷积神经网络作为分类模型的主体,通过注意力机制筛选出更有区分度的特征,使模型能够提取到更精确、更核心的空间-光谱信息,实现高光谱图像的高精度分类。对Indian Pines(IP)、University of Pavia(UP)和Salinas(SA)三个数据集进行了应用实验,结果表明,基于该模型的目标图像总体分类精度、平均分类精度和Kappa系数均高于98.14%、97.17%、97.87%。与常规HybridSN模型对比表明,HybridSN_AM模型在三个数据集上的分类精度分别提升了0.89%、0.07%和0.73%。有效解决了高光谱图像空间-光谱特征提取与融合的难题,提高HSI分类的精度,具有较强的泛化能力,充分验证了注意力机制结合混合卷积神经网络在高光谱图像分类中的有效性和可行性,对高光谱图像分类技术的发展及应用具有重要的科学价值。
