基于改进Hough变换的线性目标检测

为提高检测高分辨率遥感影像中线性目标的精度,通过分析线性目标的几何特征,提出了一种用于检测线性目标的改进Hough变换算法。将Freeman链码和Hough变换相结合,采用对线性目标的边缘链码进行Hough变换的策略,有效地解决了重复检测、效率低、精度差的问题。对资源三号卫星影像进行实验,实验结果表明,该算法能有效地检测图像中的平行线性目标,实时处理性好。

资源三号卫星影像中线性目标的检测技术

为了有效地进行高分辨率图像中线性目标的检测,提出一种基于Freeman链码的改进型Hough变换算法。首先,对图像进行增强和滤波处理,采用基于灰度一致化的方法对图像进行区域分割;然后,利用Freeman编码提取目标区域的边界;最后,对链码数据进行Hough变换,检测出平行线性结构。实验结果证明:该算法能有效地提取图像中平行线性目标,将其应用于资源三号卫星影像道路网目标的识别中,准确率高且实时处理性好。

一种基于概率Hough变换的遥感图像中线目标检测新方法

线状目标检测是遥感图像中人造目标识别的重要环节,其技术关键是如何有效地从背景中提取目标的长直边缘。Hough变换是从图像中检测直线的经典方法,但遥感影像的画幅大、背景复杂,标准的Hough变换会检测出大量短直线而影响对有用目标的检测效果。本文提出了一种改进的概率Hough变换方法,首先对原始遥感影像分块,利用Canny算子检测出每个子图像的边缘,再通过Hough变换检测出每个子图中的直线,并对其中的短直线聚类分组以排除干扰,最后再从剩下线段中提取并筛选出平行线以完成长直线目标检测。实验表明,这种方法对复杂背景下的遥感影像中的线状目标有良好的检测效果。

BACKSIDE EFFECT OF BISTATIC AIRBORNE CLUTTER CHARACTERISTICS AND ITS APPLICATIONS IN GMTI

An interesting clutter characteristic of bistatic radars is presented, which is named as backside effect. In such an effect, the range-dependent ground clutter spectrum can be easily aligned, and Space-Time Adaptive Processing (STAP) is to be more applicable and effective for the Ground Moving Target Indication (GMTI) in bistatic systems. The backside effect is proved by the numerical calculation method and explained in point of the geometry. At last a new spectrum aligning method is induced, i.e., ADC and Rotation (ADCR), which can gain a further performance improvement on GMTI.