共查询到19条相似文献，搜索用时 203 毫秒
1.
一种基于局部K-分布的新的SAR图像舰船检测算法 总被引：1，自引：0，他引：1
提出了一种基于局部K-分布的新的SAR图像舰船检测算法.取目标窗口和背景窗口,通过把泄露到背景窗口中的舰船部分去除,对背景窗口中的剩余部分统计均值和方差,最终得到杂波分布概率模型进行恒虚警检测.相对于K-分布CFAR检测算法和基于局部窗口的K-分布CFAR检测算法,该算法能够适应杂波的局部变化, 对距离很近的舰船不会产生漏检.仿真结果表明了方法的有效性. 相似文献
2.
3.
分析了在海杂波背景下检测目标的特点,并针对不同类型的雷这回波,给出了几种常用的海杂波幅度统计模型及参数估计方法,为雷达滤波嚣的设计提供了理论参考. 相似文献
4.
利用IPIX雷达回波数据分析了海杂波的统计特性.并利用LFM信号在分数阶Fourier域良好的能量聚集性,提出基于分数阶Fourier变换的海面动目标检测方法.此方法能较好的聚集动目标回波能量,而对海杂波回波的能量聚集不明显,可以较好的检测出动目标.最后采用实测海杂波数据做了仿真分析,证实了此方法的有效性. 相似文献
5.
提出了一种基于经验模式分解去斑和顶帽变换背景不均匀的预处理方法. 经验模式分解去斑算法先对图像每一列进行经验模式分解得到IMF函数,然后将原信号与第一、二模态相减得到初步处理图像,再对该图像每一行重复该操作从而得到去斑图像,该算法有效地去除斑点噪声;顶帽变换则有效地补偿了海浪带来的局部不均匀的背景亮度,提高了图像的信杂比,有利于目标的检测. 仿真结果证明了算法的有效性. 相似文献
6.
7.
8.
文章采用SIRP方法实现了基于K分布的高分辨率雷达海杂波模型的仿真,K分布不仅能在很宽的条件范围内与海杂波的幅度分布很好的匹配,而且还可以正确的模拟海杂波回波脉冲间的相关特性.仿真结果证明了该方法的准确、可行. 相似文献
9.
针对杂波环境中的三维机动目标的点迹提取问题,提出了一种基于hough变换的目标点迹提取算法,将三维机动目标分别进行平面映射,然后在每个平面采用hough变换处理,对变换结果进行检测,得到所需要的目标点迹信息。采用该算法得到的目标点迹距离和角度信息,可快速起始杂波环境中的目标航迹,并降低数据处理的运算量。仿真结果表明,该算法具有较好的点迹提取能力。 相似文献
10.
弱小目标的检测与跟踪是当前雷达信号处理研究的热点。文章介绍了一种新的弱小目标检测跟踪技术,该技术基于生物视觉感知机理,将图像处理方法融入雷达信号处理,分析目标特征和杂波、噪声等背景特性,在此基础上探讨有效的背景抑制方法,并结合多特征信息融合方法实现在复杂背景下对弱小目标的检测与跟踪。 相似文献
11.
《Information processing & management》2023,60(4):103372
The unsupervised 3D model retrieval is designed to joint the information of well-labeled 2D domain and unlabeled 3D domain to learn collaborative representations. Most existing methods adopted semantic alignment, but were inevitably affected by false pseudo-label. In this paper, we design a novel Instance-Prototype Similarity Consistency Network (IPSC) to guide domain alignment with similarity consistency, which can simultaneously suppress the impact of false pseudo-label information and well reduce the domain discrepancy. IPSC contains two similarity strategies, named Single instance vs Multiple prototypes and Instance-pair vs Single prototype. The first strategy utilizes a single instance as an anchor, and measures the similarities between the anchor and multiple prototypes with the same category but from different domains. The minimization between these similarities can better align the cross-domain prototypes with Kullback–Leibler (KL) divergence than traditional Euclidean similarities. The second strategy utilizes a single prototype as an anchor, and measures the similarities between this anchor and an instance-pair with the same category but from different domains. The minimization between these similarities can conduct the instance-level alignment with KL divergence, which can better suppress the negative effect of noisy pseudo-labels. We conduct various experiments on two datasets, MI3DOR-1 (21000 2D images and 7690 3D models) and MI3DOR-2 (19694 2D images and 3982 3D models), to verify the superiority of our algorithm. 相似文献
12.
《Journal of The Franklin Institute》2022,359(9):4449-4467
A novel ground-moving target detection method is introduced using a distinguishing target, and clutter feature for airborne radar. The clutter proximity feature is extracted based on the Euclidean distance between a signal pixel and the expected clutter ridge in the angle-Doppler domain. Subsequently, target and clutter pixels are classified based on the extracted features for target detection without actually removing clutters or clutter estimation. The proposed technique is especially suitable for effective airborne radar target detection in the unknown ground clutter. The experimental results have validated the effectiveness of the new approach, which enables ground moving target detection in inhomogeneous clutter. 相似文献
13.
《Information processing & management》2022,59(1):102726
In synthetic aperture radar (SAR) image change detection, the deep learning has attracted increasingly more attention because the difference images (DIs) of traditional unsupervised technology are vulnerable to speckle noise. However, most of the existing deep networks do not constrain the distributional characteristics of the hidden space, which may affect the feature representation performance. This paper proposes a variational autoencoder (VAE) network with the siamese structure to detect changes in SAR images. The VAE encodes the input as a probability distribution in the hidden space to obtain regular hidden layer features with a good representation ability. Furthermore, subnetworks with the same parameters and structure can extract the spatial consistency features of the original image, which is conducive to the subsequent classification. The proposed method includes three main steps. First, the training samples are selected based on the false labels generated by a clustering algorithm. Then, we train the proposed model with the semisupervised learning strategy, including unsupervised feature learning and supervised network fine-tuning. Finally, input the original data instead of the DIs in the trained network to obtain the change detection results. The experimental results on four real SAR datasets show the effectiveness and robustness of the proposed method. 相似文献
14.
Mohamed B. El Mashade 《Journal of The Franklin Institute》2005,342(5):521-550
The radar signals returning from the targets being illuminated are usually accompanied by thermal noise and clutter. Constant false alarm rate (CFAR) processors are useful for detecting these targets in a background for which the parameters of the statistical distribution are not known and may be nonstationary. The ordered-statistics (OS) CFAR technique has been proven to work satisfactorily in both multiple-target and nonuniform clutter cases. Unfortunately, the large processing time taken by this scheme limits its practical uses. The modified versions of the OS processor have been proposed to replace it in these applications. They can reduce the processing time of the single-window OS detector in half without changing its useful properties. Our goal in this paper is to provide a complete detection analysis for the OS processor along with ordered-statistic greatest-of (OSGO) and ordered-statistic smallest-of (OSSO) modified versions, for M postdetection integrated pulses when the operating environment is nonideal. Analytical results of performance are presented in both multiple-target situations and in regions of clutter power transitions. The primary and the secondary interfering targets are assumed to be fluctuating in accordance with the Swerling II target fluctuation model. As the number of noncoherently integrated pulses increases, lower threshold values and consequently better detection performances are obtained in both homogeneous and multiple-target background models. However, the false alarm rate performance of OSSO-CFAR scheme at clutter edges worsens with increasing the postdetection integrated pulses. As predicted, the OSGO-CFAR detector accommodates the presence of spurious targets in the reference window, given that their number is within its allowable range in each local window, and controls the rate of false alarm when the contents of the reference cells have clutter boundaries. The OSSO-CFAR scheme is useful in the situation where there is a cluster of radar targets amongst the estimation cells. 相似文献
15.
16.
基于种子点增长的SAR图像海岸线自动提取算法 总被引：9，自引：0，他引：9
SAR图像中斑点噪声的存在使得很难利用简单的阈值分割技术对其进行海岸线提取，而很多基于复杂数学模型的提取算法又常常由于较慢的检测速度限制了它们的应用。本文基于种子点增长的思想，给出了一种快速的海岸线自动提取算法。首先该算法利用象素值统计信息自动定位一个初始种子点区域，并计算初始均值M与初始阈值T。然后基于不断更新的M和T进行海域点增长。增长结束后，对得到的连通海域进行轮廓边界跟踪从而确定出具体的海岸线位置。将其应用于真实的SAR图像，证明了该算法的有效性和实时性。 相似文献
17.
通过对灰度图像的边缘检测的研究,构造了一种新的基于色度差的边缘检测算法,并充分利用彩色图像的颜色信息,将此算法从灰度图像转化到RGB的颜色空间中。这种新方法旨在区别于传统意义上对图像的边缘检测要求的精准性,而把提取出彩色图像中直观形象的轮廓信息作为研究目的。实验仿真表明,该算法提取出的边缘能够较好地反映目标图像中具有代表性的信息。 相似文献
18.
Harris角点检测需要计算图像中每一个像素点的角点响应函数值(CRF),这使得算法运行速度慢,不能满足实时性的要求。针对这个缺点,文章提出了一种改进算法。改进算法通过分析图像中每个像素点8邻域范围内相似像素点分布情况,剔除那些非角点的像素点,并选出潜在的角点像素点作为下一步Harris检测的候选点,从而大大提高了算法的运行效率。 相似文献
19.
在实际的SAR场景中,由于载机平台运动的不规律会引入相位误差,这将导致SAR图像出现模糊,甚至不能形成图像,因此需要准确地估计和补偿相位误差.提出一种较好的SAR相位历史估计算法,在方位向应用延时自相关方法进行准确的相位估计,由此实现SAR的准确聚焦成像.该相位估计方法具有较高的计算效率,非常适合于实时SAR系统.利用对实际SAR数据的聚焦处理证明了该方法的有效性. 相似文献