Hello my beautiful computer vision lovers. Can anyone tell me the best way to do image segmentation with opencv, i tried watershed method as mentioned in opencv:Image segmentation with distance transform with watershed methode
but i'm really dissapointed by seeing the result, i want something which can be used in real life not just for some technical fun or some small project, since i believe in real life application only. method. So is their more better method of image segmentation in opencv, or do anyone have implemented his own than if possible share with me. Thank u:>
My program used ros to subscribe an image topic from a simulated kinect sensor from gazebo than used it for image segmentation:
#include <ros/ros.h>
#include <image_transport/image_transport.h>
#include <cv_bridge/cv_bridge.h>
#include <sensor_msgs/image_encodings.h>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/opencv.hpp>
#include <iostream>
using namespace std;
using namespace cv;
static const std::string OPENCV_WINDOW = "Image window";
class ImageConverter
{
ros::NodeHandle nh_;
image_transport::ImageTransport it_;
image_transport::Subscriber image_sub_;
image_transport::Publisher image_pub_;
public:
ImageConverter()
: it_(nh_)
{
// Subscrive to input video feed and publish output video feed
image_sub_ = it_.subscribe("/camera/rgb/image_raw", 1,
&ImageConverter::imageCb, this);
image_pub_ = it_.advertise("/image_converter/output_video", 1);
cv::namedWindow(OPENCV_WINDOW);
}
~ImageConverter()
{
cv::destroyWindow(OPENCV_WINDOW);
}
void imageCb(const sensor_msgs::ImageConstPtr& msg)
{
cv_bridge::CvImagePtr cv_ptr;
try
{
cv_ptr = cv_bridge::toCvCopy(msg, sensor_msgs::image_encodings::BGR8);
}
catch (cv_bridge::Exception& e)
{
ROS_ERROR("cv_bridge exception: %s", e.what());
return;
}
// Draw an example circle on the video stream
if (cv_ptr->image.rows > 60 && cv_ptr->image.cols > 60)
cv::circle(cv_ptr->image, cv::Point(50, 50), 10, CV_RGB(255,0,0));
// Load the image
Mat src = cv_ptr->image;
// Show source image
imshow("Source Image", src);
// Change the background from white to black, since that will help later to extract
// better results during the use of Distance Transform
for( int x = 0; x < src.rows; x++ ) {
for( int y = 0; y < src.cols; y++ ) {
if ( src.at<Vec3b>(x, y) == Vec3b(255,255,255) ) {
src.at<Vec3b>(x, y)[0] = 0;
src.at<Vec3b>(x, y)[1] = 0;
src.at<Vec3b>(x, y)[2] = 0;
}
}
}
// Show output image
imshow("Black Background Image", src);
// Create a kernel that we will use for accuting/sharpening our image
Mat kernel = (Mat_<float>(3,3) <<
1, 1, 1,
1, -8, 1,
1, 1, 1); // an approximation of second derivative, a quite strong kernel
// do the laplacian filtering as it is
// well, we need to convert everything in something more deeper then CV_8U
// because the kernel has some negative values,
// and we can expect in general to have a Laplacian image with negative values
// BUT a 8bits unsigned int (the one we are working with) can contain values from 0 to 255
// so the possible negative number will be truncated
Mat imgLaplacian;
Mat sharp = src; // copy source image to another temporary one
filter2D(sharp, imgLaplacian, CV_32F, kernel);
src.convertTo(sharp, CV_32F);
Mat imgResult = sharp - imgLaplacian;
// convert back to 8bits gray scale
imgResult.convertTo(imgResult, CV_8UC3);
imgLaplacian.convertTo(imgLaplacian, CV_8UC3);
// imshow( "Laplace Filtered Image", imgLaplacian );
imshow( "New Sharped Image", imgResult );
src = imgResult; // copy back
// Create binary image from source image
Mat bw;
cvtColor(src, bw, CV_BGR2GRAY);
threshold(bw, bw, 40, 255, CV_THRESH_BINARY | CV_THRESH_OTSU);
imshow("Binary Image", bw);
// Perform the distance transform algorithm
Mat dist;
distanceTransform(bw, dist, CV_DIST_L2, 3);
// Normalize the distance image for range = {0.0, 1.0}
// so we can visualize and threshold it
normalize(dist, dist, 0, 1., NORM_MINMAX);
imshow("Distance Transform Image", dist);
// Threshold to obtain the peaks
// This will be the markers for the foreground objects
threshold(dist, dist, .4, 1., CV_THRESH_BINARY);
// Dilate a bit the dist image
Mat kernel1 = Mat::ones(3, 3, CV_8UC1);
dilate(dist, dist, kernel1);
imshow("Peaks", dist);
// Create the CV_8U version of the distance image
// It is needed for findContours()
Mat dist_8u;
dist.convertTo(dist_8u, CV_8U);
// Find total markers
vector<vector<Point> > contours;
findContours(dist_8u, contours, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE);
// Create the marker image for the watershed algorithm
Mat markers = Mat::zeros(dist.size(), CV_32SC1);
// Draw the foreground markers
for (size_t i = 0; i < contours.size(); i++)
drawContours(markers, contours, static_cast<int>(i), Scalar::all(static_cast<int>(i)+1), -1);
// Draw the background marker
circle(markers, Point(5,5), 3, CV_RGB(255,255,255), -1);
imshow("Markers", markers*10000);
// Perform the watershed algorithm
watershed(src, markers);
Mat mark = Mat::zeros(markers.size(), CV_8UC1);
markers.convertTo(mark, CV_8UC1);
bitwise_not(mark, mark);
// imshow("Markers_v2", mark); // uncomment this if you want to see how the mark
// image looks like at that point
// Generate random colors
vector<Vec3b> colors;
for (size_t i = 0; i < contours.size(); i++)
{
int b = theRNG().uniform(0, 255);
int g = theRNG().uniform(0, 255);
int r = theRNG().uniform(0, 255);
colors.push_back(Vec3b((uchar)b, (uchar)g, (uchar)r));
}
// Create the result image
Mat dst = Mat::zeros(markers.size(), CV_8UC3);
// Fill labeled objects with random colors
for (int i = 0; i < markers.rows; i++)
{
for (int j = 0; j < markers.cols; j++)
{
int index = markers.at<int>(i,j);
if (index > 0 && index <= static_cast<int>(contours.size()))
dst.at<Vec3b>(i,j) = colors[index-1];
else
dst.at<Vec3b>(i,j) = Vec3b(0,0,0);
}
}
// Visualize the final image
imshow("Final Result", dst);
waitKey(0);
}
};
int main(int argc, char** argv)
{
ros::init(argc, argv, "image_converter");
ImageConverter ic;
ros::spin();
return 0;
}
