使用卫星校正多光谱图像进行边缘检测
我正在尝试使用 MATLAB 将 sobel
和 canny
边缘检测方法应用于校正的多光谱卫星图像,但它无法检测边缘。结果不是边缘而是遍布各处的点状噪声。
我应该怎么做才能从校正的多光谱图像中检测出微妙的边界?需要什么特殊的技术吗?
I am trying to apply sobel
and canny
edge detection methods using MATLAB to a rectified Multispectral Satellite imagery, but it couldn't detect the edges. The results were just not as edges but as dotted noise all over.
What should I do to detect the delicate boundaries from the rectified multispectral imagery? Is there any special technique needed?
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论
评论(2)
作为一个选项,您可以保存 RGB 图像并尝试使用 Outliner 实用程序打开它们
http://outliner.codeplex.com/
该实用程序使用一种最适合彩色图像的边缘检测替代方法。
As an option, you can save your RGB images and try to open them with the Outliner utility
http://outliner.codeplex.com/
This utility uses an alternative method of edge detection that works best on color images.
假设您正确执行了其他所有操作(如何调用
edge
命令等),如果图像特别嘈杂,则可能会发生这种情况。您可能会考虑进行平滑(例如使用高斯或其他内核进行过滤)。这应该会使噪声消失,有利于其他更有意义的边缘。您还应该尝试使用阈值。
Assuming you're doing everything else right (with how you're calling the
edge
command etc.) this can happen if the images are particularly noisy. You might consider smoothing (such as filtering with a Gaussian or other kernel.) This should make the noise go away in favor of other more meaningful edges.You should also try play with the thresholds.