grabcut 图像目标分割（1）

最新推荐文章于 2024-07-27 12:48:21 发布

xiaotingting_

最新推荐文章于 2024-07-27 12:48:21 发布

阅读量497

点赞数

分类专栏： opencv学习笔记

本文链接：https://blog.csdn.net/xiaotingting_/article/details/79432381

版权

opencv学习笔记专栏收录该内容

6 篇文章 0 订阅

订阅专栏

本文通过OpenCV库实现GrabCut图像目标分割，展示如何利用鼠标交互选取对象并进行初步的图像处理。实验结果显示，对于灰度图和HSV图像，GrabCut能提供更清晰的分割边缘。讨论了手动选择矩形区域对结果的影响，并表达了对自动化目标区域识别的期望。

摘要由CSDN通过智能技术生成

代码：

#include<opencv2/opencv.hpp>
bool selectObject = false;
cv::Point origin;
cv::Rect selection;
cv::Mat src;
cv::Mat srcMarks;
cv::Mat result;
cv::Mat foreground;
void GrabCutSegment();
void onMouse(int event, int x, int y, int, void*)
{
if (selectObject)
{
selection.x = MIN(x, origin.x);
selection.y = MIN(y, origin.y);
selection.width = std::abs(x - origin.x);
selection.height = std::abs(y - origin.y);

selection &= cv::Rect(0, 0, src.cols, src.rows);
}
switch (event)
{
case cv::EVENT_LBUTTONDOWN:
origin = cv::Point(x, y);
selection = cv::Rect(x, y, 0, 0);
selectObject = true;
break;
case cv::EVENT_LBUTTONDOWN && cv::EVENT_MOUSEMOVE:
src.copyTo(srcMarks);
cv::rectangle(srcMarks, selection, cv::Scalar(255, 0, 0));
imshow("srcMarks", srcMarks);
break;
case cv::EVENT_LBUTTONUP:
selectObject = false;
if (selection.width != 0 && selection.height != 0){
GrabCutSegment();
}
break;
}
}

void GrabCutSegment(){
cv::Mat bgModel, fgModel;
cv::grabCut(src, result, selection, bgModel, fgModel, 5, cv::GC_INIT_WITH_RECT);
cv::compare(result, cv::GC_PR_FGD, result, cv::CMP_EQ);
// Generate output image
foreground = cv::Mat::ones(src.size(), CV_8UC3);
src.copyTo(foreground, result); // bg pixels not copied

cv::imshow("segment", foreground);
}
int main(){
src = cv::imread("hui.png");
cv::namedWindow("src",CV_WINDOW_NORMAL);
cv::imshow("src", src);

cv::namedWindow("srcMarks",CV_WINDOW_NORMAL);
src.copyTo(srcMarks);
cv::setMouseCallback("srcMarks", onMouse, 0);
cv::imshow("srcMarks", srcMarks);

cv::waitKey();