分支点（OpenCV，C ++） [英] Branching points(OpenCV,C++)

问题描述

我想在此图片中找出闪电的分支点：

I want to identify the branching points of the lightning in this image:

http://i.stack.imgur.com/PXujf.jpg

我先做的是阈值图像使得我得到图像的lighning部分
并丢弃背景。这是结果

What I did first was threshold the image such that I get the lighning part of the image and discard the backround. This is the result

http：// i.stack.imgur.com/IYNTi.jpg

我在openCV中使用了阈值函数，结果图像非常糟糕
as质量丢失，树枝不再可见。

I used the threshold function in openCV and the resulting image is pretty much bad as the quality is lost, the branches are no longer visible.

好的，基本上我有2个问题：

Ok, basically I have 2 problems:

1. 如何正确分割图像，以便正确捕捉图像的闪电部分。


2. 我如何确定分支点？对于每个分支点我想要
   在它上面画一个红色圆圈。

提前感谢你

推荐答案

细分/阈值处理


我会给这个一试。
他们还有一份关于图像分割的NIPS2012研讨会（DISCML）论文，似乎可以处理相当优雅的细长物体（如图中的闪电）。

Segmentation / thresholding:
I would give this a try. They also had a NIPS2012 workshop (DISCML) paper on image segmentation that seems to handle quite elegantly thin elongated objects (like the lightnings in the picture).

分支点：

一旦你有一个好的面具，你可以使用形态操作来提取分支点（Matlab代码）：

Branching points:
Once you have a good mask you can use morphological operations to extract the branching points (Matlab code):

 bw = myGoodSegmentation( img ); % replace with whatever segmentation/thresholding that works best for you.
 tbw = bwmorph( bw, 'skel', inf );
 [y x] = find( bwmorph( tbw, 'branchpoints' ) ); % get x,y coordinates of branch points

这篇关于分支点（OpenCV，C ++）的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！