Multiple kernel relevance vector machine for geospatial objects detection in high-resolution remote sensing images

Geospatial objects detection within complex environment is a challenging problem in remote sensing area. In this paper, we derive an extension of the Relevance Vector Machine (RVM) technique to multiple kernel version. The proposed method learns an optimal kernel combination and the associated classifier simultaneously. Two feature types are extracted from images, forming basis kernels. Then these basis kernels are weighted combined and resulted the composite kernel exploits interesting points and appearance information of objects simultaneously. Weights and the detection model are finally learnt by a new algorithm. Experimental results show that the proposed method improve detection accuracy to above 88%, yields good interpretation for the selected subset of features and appears sparser than traditional single-kernel RVMs.     

Novel method of moving target detection for dual-channel was radar based on compressed sensing

We propose a ground moving target detection method for dual-channel Wide Area Sur- veillance （WAS） radar based on Compressed Sensing （CS）. Firstly, the method of moving target detection of the WAS radar is studied. In order to reduce the sample data quantity of the radar, the echo data is randomly sampled in the azimuth direction, then, the matched filter is used to perform the range direction focus. We can use the compressive sensing theory to recover the signal in the Doppler domain. At last, the phase difference between the two channels is compensated to suppress the clutter. The result of the simulated data verifies the effectiveness of the proposed method.     

非合作区域星载遥感图像的车辆目标检测

针对非合作区域遥感图像中复杂背景下车辆目标检 测困难的问题, 提出一种改进形态学重建的车辆目标检测方法。首先,利用遥感图像的近红外和红色波段的 信息,获取场 景的归一化植被指数(NDVI),去除植被背景的干扰;其次,设计方向模板, 对全色图像进行滤波,使人 造物背景得以完整保留,并生成标记图像,利用标记图像重建得到人造物背景;最后,利用 原图和重建背 景之间的差异,进行车辆检测,有效消除了复杂背景的干扰。将本文提出的方法应用于实际 遥感图像的车 辆目标检测,结果表明,检测效果好,鲁棒性强,无需先验信息,可用于大幅面遥感 图像的车辆目标自动提取。     

融合多特征的对象级航空遥感图像变化检测

针对航空遥感图像,构建一种面向对象的融合JS(Jensen-Shannon)散度特征与互相关特征的变化检测算法。首先,应用多尺度分割算法获取像斑;然后,提取反映像斑内像素灰度分布的总体统计特征的JS散度以及反映像斑内部结构的变化特征的互相关特征,应用决策级融合方案对两个优势互补的特征进行有效融合,进而探测变化区域;最后与固定权重融合的检测结果进行精度对比。结果表明:本文方法的平均检测精度达到93.07%,误检率平均为7.13%,漏检率平均为4.37%,比仅基于JS散度特征、互相关特征、固定权重融合的检测方法精度分别提高了8.98%、4.71%和4.20%。因此,该变化检测方法不仅能有效提取变化区域,而且提高了变化检测的精度,在航空遥感图像变化检测中具有有效性与应用潜力。     

亚米级全色遥感影像云地检测算法研究

为解决现行云地检测算法不适用于亚米级全色遥感 影像云地检测的问题,提出一种大尺度自适应匹配阈值(LS-AMTH,large-scale adaptiv e matching threshold)算法。算法构建包含光谱、纹理 与边缘特征的特征参量集,利用提升算法对影像子块进行大尺度云地分类;之后对大尺度分 类所得云地子 块进行阈值的自适应匹配选择,最终实现像素级云地区域检测并统计云地占比。试验表明, 针对亚米级全 色影像,本文算法准确度达97.3%,在复杂云地混合区域取得良好检 测效果。     

YOLOv5-LR：一种遥感影像旋转目标检测模型

真实遥感图像中,目标呈现任意方向分布的特点,原始YOLOv5网络存在难以准确表达目标的位置和范围、以及检测速度一般的问题。针对上述问题,提出一种遥感影像旋转目标检测模型YOLOv5-Left-Rotation,首先利用Transformer自注意力机制,让模型更加注意感兴趣的目标,并且在图像预处理过程中采用Mosaic数据增强,对后处理过程使用改进后的非极大值抑制算法Non-Maximum Suppression。其次,引入角度损失函数,增加网络的输出维度,得到旋转矩形的预测框。最后,在网络模型的浅层阶段,增加滑动窗口分支,来提高大尺寸遥感稀疏目标的检测效率。实验数据集为自制飞机数据集CASIA-plane78和公开的舰船数据集HRSC2016,结果表明,改进旋转目标检测算法相比于原始YOLOv5网络的平均精度提升了3.175%,在吉林一号某星推扫出的大尺寸多光谱影像中推理速度提升了13.6%,能够尽可能地减少冗余背景信息,更加准确检测出光学遥感图像中排列密集、分布无规律的感兴趣目标的区域。     

Object-based change detection method for high-resolution remote sensing image combining shadow compensation and multi-scale fusion

As an interpreting symbol of remote sensing images,shadow,however,brings about “pseudo changes”,which is one of the main sources leading to error detection in high-resolution remote sensing image change detection.For this issue,an object-based high-resolution remote sensing image change detection method was proposed combining with shadow compensation and multi-scale fusion.In the object orientation detection framework,the shadows in the remote sensing images were extracted.Then multi-scale change detection was conducted with shadow compensation.In the process,an objective function was constructed of mutual scale information minimization to realize the adaptive extraction of scale parameters.Based on this,combined with the shadow compensation factor,a multi-scale decision-level fusion strategy built on D-S theory of evidence was designed,and the levels of change intensity were further divided.The experiments show that the method is effective in solving the error detection problem caused by shadow,significantly improving the precision of change detection.     

一种新的无监督的卫星影像变化检测算法

提出了一种基于主分量分析(PCA)和上下截集模糊Kohonen聚类网络(UDSFKCN)的、无监督的、不同时相的和卫星影像的像素级变化检测新算法.将PCA和UDSFKCN两种方法结合,并将它应用于不同时相的卫星影像的变化检测.该方法结合每个像素的邻域信息,利用PCA,产生每个像素对应的基于邻域信息的特征向量;又将变化区...     

城市街区星载光学遥感图像车辆目标自动检测方法

针对星载光学遥感图像城市街区复杂背景问题,提出一种车辆目标自动检测方法.首先,利用场景中植被背景的物理属性,通过多光谱波段抑制场景中的植被背景,然后,在分析城市街区地物形态反射率特性的基础上,利用全色波段并结合二值形态学方法抑制场景中的建筑物,最后,引入著名的RX算法对抑制后的图像进行车辆目标检测.将文中提出的方法应用于实际Quickbird影像的车辆目标检测,结果表明所提出的方法具有鲁棒性强,执行效率高,不需要人工辅助等方面的特点,可用于城市街区车辆目标的自动检测.     

基于邻域信息的SAR图像变化检测

为了减少合成孔径雷达(SAR)图像中乘性斑点噪声对变化检测结果的影响,充分地利用了像素的邻域信息。首先使用邻域比值(NR)方法构造差异图像,然后提出基于邻域信息的模糊C均值聚类(FCM)算法。NR算子在构造差异图像时能够较好地保留图像信息并抑制噪声的干扰。同时将邻域信息引入到FCM算法的目标函数,以邻域加权距离改进了FCM算法在欧式距离计算中的不足,并约束了隶属度函数,减少了噪声对邻域中心像素的干扰。通过以上考虑像素邻域信息的算法,得到了差异图像的聚类结果,从而实现了SAR图像的变化检测。实验结果表明,所提算法较传统的FCM和K-means聚类算法,可以较好地保留图像变化区域的信息,同时提高了SAR图像变化检测的准确度。     

聚类与几何特征相结合的遥感图像多类人造目标检测算法

针对高分辨率光学遥感图像中人造目标的检测问 题,对传统的相位编组直线段提取算法和k-means 聚类算法了改进,提出了一种k-means聚类和几何特征 相结合的检测方法。根据自然物体和 人造目标在几何外形上表现出的不同特性,首先运用改进的相位编组算法对图像进行快速的 直线段提取; 然后以获取的直线段中心点为处理对象,运用k-means聚类算法 对提取的直线段进行密度聚类;最后,根 据每个类中的直线段数目和构成的几何基元情况,进行人造目标的判定。实验结果表明,本 文算法对遥感 图像中的房屋、汽车、船舰和飞机跑道等多类人造目标可达到90%以 上的检测精度,并具有较高的检测速度,对于一幅512pixel ×512pixel的图像,整个检测过程在100ms 以内。     

遥感图像自适应分层量化的快速DCT压缩法

依据遥感图像的频谱特性,提出一种自适应分层量化的快速DCT图像压缩算法,在对原始图像快速DCT之后,根据图像频谱特性自适应修正JPEG量化表,再用新量化表分层量化DCT系数。真实遥感图像压缩实验表明,在同等压缩比下,提出的方法比标准JPEG方法速度快,且峰值信噪比增加1～2dB,并能实现嵌入式码流图像压缩。     

基于协方差矩阵特征分解的多通道SAR-GMTI方法及性能分析

该文提出了一种基于协方差矩阵特征分解的多通道运动目标检测和测速定位方法,该方法依据多通道SAR数据协方差矩阵特征分解后小特征值和的幅度变化来检测运动目标。在检测出运动目标后,先利用两幅复图像的干涉相位对目标径向速度进行粗略估计,再通过搜索动目标空域导向矢量的方法对径向速度进行精确估计,克服了干涉相位对杂波和噪声的敏感性。仿真数据和实测数据验证了该方法的有效性。     

SAR图像上舰船目标检测的一种新算法

提出了一种改进的KSW算法检测SAR图像上的舰船目标.在该算法中,检测门限被选择以最大化背景与目标灰度熵加权和.由于加权系数的引入,该算法能针对SAR图像上舰船目标检测的实际情况,调整背景与目标灰度熵在准则函数中所占比例.当海杂波较弱时,该算法与传统的KSW算法等价.当海杂波较强时,其较传统的KSW算法有更好的表现.     

复杂杂波背景下海洋SAR图像中舰船目标的检测

针对卫星SAR图像海洋背景和舰船目标特点,文献[1]提出了基于小波多分辨率分析的卫星SAR海洋图像舰船目标检测的新方法。在此基础上,本文针对不同海情杂波服从不同概率密度分布的特点,讨论了复杂杂波背景下基于小波变换检测海洋SAR图像中舰船目标的性能,给出了不同海情下的检测性能,并与传统门限检测方法比较,给出了不同信杂比下虚警概率曲线。仿真结果表明,该方法实用、有效。     

基于ROC融合准则的SAR边缘检测算法

根据ROC(receiver operating characteristics)技术能评估分类器在所有可能工作阈值下总体性能的特点,建立包含边缘像素点相关分析与ROC分类决策的ROC融合准则。依据该准则组合多种SAR边缘检测算子,并得到合成孔径雷达(SAR)影像的"理想"边缘检测结果。实验结果表明,本文方法能融合多种边缘检测算子的优点,有较强的开放性与目标适应性,并且不需要手工设置阈值,自动化程度高,有很强的工程实用性。     

Maximum A Posteriori -based automatic target detection in SAR images

The paper presents an algorithm of automatic target detection in Synthetic Aperture Radar(SAR) images based on Maximum A Posteriori(MAP). The algorithm is divided into three steps. First, it employs Gaussian mixture distribution to approximate and estimate multi-modal histogram of SAR image. Then, based on the principle of MAP, when a priori probability is both unknown and learned respectively, the sample pixels are classified into different classes c = {target, shadow, background}. Last, it compares the results of two different target detections. Simulation results preferably indicate that the presented algorithm is fast and robust, with the learned a priori probability, an approach to target detection is reliable and promising. Communication author: Wang Yimin, born in 1968, male, Ph.D. candidate. College of Automation, Northwestern Polytechnical University, Xi’an 710072, China.     

基于NSCT域的自适应阈值遥感图像去噪方法

提出一种新的基于非下采样Contourlet变换(NSCT)的图像自适应阈值去噪方法.根据NSCT系数所在领域区域的特性,给出不同尺度不同方向的自适应咧值.仿真实验结果表明,通过本文提出的方法能够有效去除遥感图像的高斯噪声,较完整的保持图像的边缘等细节信息.与小波硬阈值、Contourlet硬阈值和基于非下采样Cont...     

Rayleigh-distribution based minimum error thresholding for SAR images

This paper presents a minimum error thresholding (MET) algorithm under the hypothesis that the gray level histogram of SAR image fits to a mixture model of shifted Rayleigh distribution. This algorithm is applied to real SAR images and compared with traditional Otsu algorithm and other MET algorithms based on various models of histogram. The hypothesis of using Rayleigh distribution model is confirmed by Kolmogorov-Smirnov testing and the comparison results obtained show that the proposed new algorithm has good performance in thresholding SAR images.     

Study on the technique to detect texture features in SAR images

This letter studies on the detection of texture features in Synthetic Aperture Radar (SAR) images. Through analyzing the feature detection method proposed by Lopes, an improved texture detection method is proposed, which can not only detect the edge and lines but also avoid stretching edge and suppressing lines of the former algorithm. Experimental results with both simulated and real SAR images verify the advantage and practicability of the improved method.