Combining beamlet transform with steerable filters, a new edge detection method based on line gradient is proposed. Compared with operators based on point local properties, the edge-detection results with this method ...Combining beamlet transform with steerable filters, a new edge detection method based on line gradient is proposed. Compared with operators based on point local properties, the edge-detection results with this method achieve higher SNR and position accuracy, and are quite helpful for image registration, object identification, etc. Some edge-detection experiments on optical and SAR images that demonstrate the significant improvement over classical edge operators axe also presented. Moreover, the template matching result based on edge information of optical reference image and SAR image also proves the validity of this method.展开更多
利用一种Beamlet变换算法来提取遥感图像中的线性特征,通过对遥感图像按二进、递归进行划分,利用灰度信息,积分计算每一小块图像中的Beamlets,结合梯度信息,通过广义似然比检验GLRT(generalized likeli-hood ratio testing)来检测判断...利用一种Beamlet变换算法来提取遥感图像中的线性特征,通过对遥感图像按二进、递归进行划分,利用灰度信息,积分计算每一小块图像中的Beamlets,结合梯度信息,通过广义似然比检验GLRT(generalized likeli-hood ratio testing)来检测判断符合条件假设的Beamlets,重建线性目标。此算法可以克服图像中的干扰及噪声,适应复杂、低信噪比遥感图像环境,准确地定位出直线。实验结果表明,该算法具有较好的性能,可以应用到实际的遥感图像处理中,具有实用价值。展开更多
文摘Combining beamlet transform with steerable filters, a new edge detection method based on line gradient is proposed. Compared with operators based on point local properties, the edge-detection results with this method achieve higher SNR and position accuracy, and are quite helpful for image registration, object identification, etc. Some edge-detection experiments on optical and SAR images that demonstrate the significant improvement over classical edge operators axe also presented. Moreover, the template matching result based on edge information of optical reference image and SAR image also proves the validity of this method.
文摘利用一种Beamlet变换算法来提取遥感图像中的线性特征,通过对遥感图像按二进、递归进行划分,利用灰度信息,积分计算每一小块图像中的Beamlets,结合梯度信息,通过广义似然比检验GLRT(generalized likeli-hood ratio testing)来检测判断符合条件假设的Beamlets,重建线性目标。此算法可以克服图像中的干扰及噪声,适应复杂、低信噪比遥感图像环境,准确地定位出直线。实验结果表明,该算法具有较好的性能,可以应用到实际的遥感图像处理中,具有实用价值。
