Skip to main content

Featured Post

OpenCV 4.5 simple optical flow GPU tutorial cuda::FarnebackOpticalFlow

This OpenCV tutorial is a very simple code example of GPU Cuda optical flow in OpenCV written in c++. The configuration of the project, code, and explanation are included for farneback Optical Flow method. Farneback algorithm is a dense method that is used to process all the pixels in the given image. The dense methods are slower but more accurate as all the pixels of the image are processed. In the following example, I am displaying just a few pixes based on a grid. I am not displaying all the pixes. In the opposite to dense method the sparse method like Lucas Kanade using just a selected subset of pixels. They are faster. Both methods have specific applications. Lucas-Kanade is widely used in tracking. The farneback can be used for the analysis of more complex movement in image scene and furder segmentation based on these changes. As dense methods are slightly slower, the GPU and Cuda implementation can lead to great performance improvements to calculate optical flow for all pixels o

OpenCV 4.5 simple optical flow GPU tutorial cuda::FarnebackOpticalFlow

This OpenCV tutorial is a very simple code example of GPU Cuda optical flow in OpenCV written in c++. The configuration of the project, code, and explanation are included for farneback Optical Flow method. Farneback algorithm is a dense method that is used to process all the pixels in the given image. The dense methods are slower but more accurate as all the pixels of the image are processed. In the following example, I am displaying just a few pixes based on a grid. I am not displaying all the pixes. In the opposite to dense method the sparse method like Lucas Kanade using just a selected subset of pixels. They are faster. Both methods have specific applications. Lucas-Kanade is widely used in tracking. The farneback can be used for the analysis of more complex movement in image scene and furder segmentation based on these changes. As dense methods are slightly slower, the GPU and Cuda implementation can lead to great performance improvements to calculate optical flow for all pixels of your image. 

Opencv OpticalFlow

Content cuda::FarnebackOpticalFlow tutorial

  • Requirements to compile and run code
  • Brief description of how to compile OpenCV with Cuda
  • Visual Studio Opencv Cuda Project configuration
  • FarnebackOpticalFlow
  • Brief description of code
  • Full code

Prerequisities cuda::FarnebackOpticalFlow

  • NVIDIA CUDA Toolkit I am using version 11
  • Visual Studio 2019
  • Opencv 4.5 build from source with Cuda

Build OpenCV with Cuda contrib

The tutorial to compile Opencv with Cuda and contribution library is here. You can exclude GStreamer. 

Visual studio OpenCV Cuda configuration

The following examples show the exact setting for the Visual Studio project. Additionally to normal OpenCV configuration. You have to point to a few locations. Include directory ....CUDA\v11.0\include and additional library dependencies ....CUDA\v11.0\x64.  The last thing is to add OpenCV Cuda specific libs to additional dependencies. Just follow these pictures: 

Opencv cuda configuration visual studio

Visual studio include directory OpenCV Cuda


Opencv cuda configuration visual studio

Visual studio additional library directories OpenCV Cuda


Visual studio additional dependencies opencv cuda

Visual studio additional dependencies OpenCV Cuda

cuda::FarnebackOpticalFlow class

The use of FarnebackOpticalFlow with default parameters is very simple and straightforward. The first step is the create a pointer to the FarnebackOpticalFlow object. The Ptr in OpenCV is C++11 shared pointer. I believe that the most important advantage of this pointer to mention is automatic cleanup. 

Ptr<cuda::FarnebackOpticalFlow> farn = cuda::FarnebackOpticalFlow::create();
The actual calculation of the optical flow is done in this calc function. The first parameter is GPU mat GpuImg0 for the previous image, the second GpuImg1 is for the actual image and the flow is GpuMat, where to put the result. The calculated optical flow based on the difference between GpuImg0 and GpuImg1;  farn->calc(GpuImg0, GpuImg1, gflow);

A short explanation of OpenCV optical flow code

The flow is simple. You have to capture at least two images to calculate flow. The first run of the for the look just fills the previous image frame1.

        if (frame1.empty()) {
            frame0.copyTo(frame1);
        }

If frame1 exists just calculate the flow and update the frame1 at the end of the loop.

frame0.copyTo(frame1);

There is a few simple tricks in the code.

1) The image must be gray

 cv::cvtColor(image, frame0, cv::COLOR_BGR2GRAY);

2) Create GpuMat from Mat

frame0.copyTo(frame1);

3) Put the result from gflow GpuMat to Mat flow.

 gflow.download(flow);

4) Draw the results.

You can draw optical flow for each pixel. The original image will be lost. This is why, The x,y iterates on y +=+10 grid. The origin x,y and end point is x+Point2f x and y from the matrix flow. The 5 is the gain to amplify the size of the flow line. 

for (int y = 0; y < image.rows - 1; y += 10) {
   for (int x = 0; x < image.cols - 1; x += 10) {
   // get the flow from y, x position * 10 for better visibility
   const Point2f flowatxy = flow.at<Point2f>(y, x) * 5;
   // draw line at flow direction
   line(image, Point(x, y), Point(cvRound(x + flowatxy.x),
   cvRound(y + flowatxy.y)), Scalar(02550), 2);
   // draw initial point          https://funvision.blogspot.com
   circle(image, Point(x, y), 1Scalar(00255), -1);
   }
}

FarnebackOpticalFlow tutorial code C++

// For tutorial go to
// https://funvision.blogspot.com
#include <iostream>
#include <fstream>
#include <opencv2/cudaimgproc.hpp>
#include <opencv2/core.hpp>
#include <opencv2/video.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/cudabgsegm.hpp>
#include <opencv2/cudaobjdetect.hpp>
#include <opencv2/cudaoptflow.hpp>
#include <opencv2/videoio.hpp>
#include <opencv2/highgui.hpp>
#include "opencv2/cudaarithm.hpp"
#include <omp.h>
#include <chrono>

using namespace std;
using namespace cv;
using namespace cv::cuda

int main()
{

    Mat frame0;
    Mat frame1;
    // https://funvision.blogspot.com
    Ptr<cuda::FarnebackOpticalFlow> farn = cuda::FarnebackOpticalFlow::create();
    //Capture camera
    VideoCapture cap(0);

    for (;;) {
        Mat image;
        cap >> image;
    
        cv::cvtColor(image, frame0, cv::COLOR_BGR2GRAY);

        if (frame1.empty()) {
            frame0.copyTo(frame1);
        }
        else {
            Mat flow;
            //Put Mat into GpuMat
            GpuMat GpuImg0(frame0);
            GpuMat GpuImg1(frame1);
//Prepare space for output
            GpuMat gflow(frame0.size(), CV_32FC2);
            // chrono time to calculate the the needed time to compute and
// draw the optical flow result
            std::chrono::steady_clock::time_point begin = 
std::chrono::steady_clock::now(); 
            // Calculate optical flow
            farn->calc(GpuImg0, GpuImg1, gflow);
            // GpuMat to Mat
            gflow.download(flow);

                for (int y = 0; y < image.rows - 1; y += 10) {
                    for (int x = 0; x < image.cols - 1; x += 10) {
                        // get the flow from y, x position * 10 for better visibility
                        const Point2f flowatxy = flow.at<Point2f>(y, x) * 5;
                        // draw line at flow direction
                        line(image, Point(x, y), Point(cvRound(x + flowatxy.x),
                         cvRound(y + flowatxy.y)), Scalar(02550), 2);
                        // draw initial point  https://funvision.blogspot.com
                        circle(image, Point(x, y), 1Scalar(00255), -1);
                    }
                }

            // end - begin time to calculate compute farneback opt flow + draw
            std::chrono::steady_clock::time_point end = std::chrono::steady_clock::now();
            std::cout << "Time difference = " << 
std::chrono::duration_cast<std::chrono::milliseconds>(end - begin).count() 
<< "[ms]" << std::endl;
            // Display result  https://funvision.blogspot.com
            imshow("Display window", image);
            waitKey(25);
            // Save frame0 to frame1 to for next round
// https://funvision.blogspot.com
            frame0.copyTo(frame1);
        }
    }
}



Comments

Popular

Opencv GStreamer (windows) video streaming tutorial + full source code for RTSP HLS streaming

Opencv C++ simple tutorial to use GStreamer to send video to Server that converts RTSP to HLS video stream. The source code and all needed configurations are included.  O pencv is a powerful computer vision library. You can use it in production and use it for image and video processing and modern machine learning. In some applications, You may want to stream your processed video results from your C++ OpenCV app outside and not just use a simple OpenCV graphical interface. The video streaming of your results is what you are looking for. Do you want to stream processed video from your IoT device? Yes, This is mainly for Linux. Do you want to stream processed video to the Web player, broadcast the video or just use VLC to play video processed by OpenCV? You may be interested in reading the next lines.  Opencv video stream to VLC or WEB There are basically two main options with OpenCV. The first one is to write a streaming application using FFMPEG. This is a little bit more advanced appro

Opencv Web camera and Video streams in Windows subsystem for Linux WSL, by FFmpeg and GStreamer

Opencv in Windows Subsystem for Linux (WSL) is a compatibility layer designed to running Linux binary executables (in ELF format) natively on Windows 10. I love it. There are some limitations to mention. The first biggest is the lack of support of CUDA, which could be a limitation for deep learning application and learning in WSL. The second trouble for Opencv development is the lack of Web camera support. This suspends WSL almost on a useless level for me until now.  VideoCapture cap;   is not working in WSL for now cap.open(0);  FFMPEG to WSL opencv program and back to WEB browser in windows This Video capture is right now not possible at in Ubuntu running under Windows (WSL). I will hit this limitation in this article. I will show you how to reach a video camera and learn something more about video streaming. Yes, the opencv processed frames will be stream to the web player on simple web site. Check the goal of this opencv tutorial on this video What you will learn

Compile Opencv with GStreamer for Visual Studio 2019 on windows 10 with and contribution modules

The goal of this tutorial is a simple step by step compilation of Opencv 4.2 with contribution extra modules with GStreamer as a bonus. The environment is Windows 10, Visual Studio 2019 C++ application. This took me almost one day of correcting of CMake setting. The goal of this tutorial is: compiled a set of OpenCV libraries with GStreamer and FFmpeg on Windows. I focus mainly on GStreamer. It is a little bit more tricky. You will reach the following information about your Opencv environment by compile and run this simple code. The Opencv GStreamer is turned as YES. GStreamer gives you a great opportunity to stream OpenCV output video outside of your program, for example, web application. I recently compiled with opencv 4.4. The update at the end of the post.  It is working!! wow, The working app and configuration in future tutorials. #include   <opencv2/opencv.hpp> #include   <iostream> using namespace cv; int   main () {      std ::cout <<  &q

Opencv HSL video stream to web

This tutorial will show you all components, configuration, and code needed to steam video output results from Opencv C++ to your Web player. The C++ program will take any video input and process this video. The processed video will be stream outside of OpenCV using the GStreamer pipeline (Windows part). The HLS video produces one Playlist file and several MPEG-TS segments of videos. This several HLS outputs are stored in the Windows file system. I am using WSL 2, windows subsystem for Linux to run Ubuntu distribution. Here the NGINX is installed with the RTMP module. NGINX is distributing a video stream from the windows file system to the web.  Let's have a look at this in more detail.  What is covered? Opencv C++ part + GStreamer pipeline NGINX configuration Architecture Web Player for your HLS stream What is not covered? Detailed instalation of Opencv + Gstreamer more here  GStreamer installation  ,  GStreamer Installation 2  on windows Detailed installation of NGINX + RTMP modul

Opencv C++ Tutorial Mat resize

Opencv Mat Resize   Resize the Mat or Image in the Opencv C++ tutorial. It is obviously simple task and important to learn. This tutorial is visualized step by step and well-described each of them. The main trick is in that simple code. Mat Input; Mat Resized; int ColumnOfNewImage = 60; int RowsOfNewImage = 60; resize(Input, Resized, Size( ColumnOfNewImage , RowsOfNewImage )); This code just takes an Input image and resized save to output Mat. How big is the resized image is based on the Size? Size just contains two parameters. Simple numbers of how the result should be big. The simple number of columns (width) and rows (height). That is basically it. Enjoy                                                 Boring same face again and again.  Load Image, resize and save Opencv C++ #include <Windows.h> #include "opencv2\highgui.hpp" #include "opencv2\imgproc.hpp" #include "opencv2\video\background_segm.hpp" #include &qu

Opencv C++ tutorial : Smoothing, blur, noise reduction / canceling

Smooth or blur, gaussian blur, and noise-canceling, This tutorial will learn OpenCV blur, GaussianBlur, median blur functions in C++. Additionally, the advanced technique for noise reduction  fastNlMeansDenoising family  will be introduced with a code example for each method.   You can use blurring of the image to hide identity or reduce the noise of the image.  Blur can be a very useful operation and it is a very common operation as well. For example, the anonymization of pedestrians, face or is one possible target for blue operation. The blur is the most common task to perform over the image to reduce noise. The noise reduction is more task for Gaussian blur than for simple blur operation. The various blur operations are very common for image processing on mobile devices.  The more important is the robustness issues of the data in pre-processing for machine learning. Sometimes, by blurring the images of the dataset can have a positive effect on the robustness of the achieved de

Opencv tutorial RTMP video streaming to NGINX restream as HLS

Video streaming Tutorial of sending processed Opencv video to NGINX and distributing video from NGINX (broadcast) by HLS stream for a wider audience, like multiple web players, VLC, or any other video stream receiver. Opencv application HLS streaming by GStreamer and NGINX  We will use GStreamer to send video from the Opencv application by rtmp2sink to an RTMP module in NGINX. In our example, the server is a widely used NGINX server with an Nginx-RTMP-module. The NGINX will receive RTMP video from Opencv and restream as an HLS video stream considered for multiple end consumers. This is a follow-up to the previous article about Video streaming from Opencv to RtspSimpleServer by rtsp protocol.   The goal is the same. Send video from Opencv to the server and restream the video for a wider audience. The difference is that RtspSimpleServer running on windows, NGINX is running in docker (WSL2). The one-to-one communication between Opencv and RtspSimpleServer was established by RTSP protocol

Opencv 4 C++ Tutorial simple Background Subtraction

This method is used to learn what belongs to the background of the image and what belongs to the foreground. The static cameras that monitor the area can very easily recognize, what is part of the image that is always here or there is something that is new and moving over the background.  Background subtraction Visual studio 2019 project setup If you have Opencv 4+ compiled or installed only steps you need to do is set the include directory with OpenCV header files. Set the Additional library Directories that point to \lib folder. Just note that Visual Studio 2019 should use VC16 \lib. Finally, As additional dependencies, specify the libs used to resolve the function implementation in the code. The list for Opencv 420 is here. The different version of opencv is using different numbering for example opencv 440 will use opencv_core440.lib.  opencv_bgsegm420.lib opencv_core420.lib opencv_videoio420.lib opencv_imgproc420.lib opencv_highgui420.lib opencv_video420.lib  Background sustract

Opencv VideoCapture File, Web Camera, RTSP stream

Opencv VideoCapture File, Camera and stream Opencv tutorial simple code in C++ to capture video from File, Ip camera stream and also the web camera plug into the computer. The key is to have installed the FFMPEG especially in case of reading the stream of IP cameras. In windows just use Opencv Installation by Nugets packages  Here . Simple easy under 2 minutes of installation. In Linux, you need to follow the instruction below. If you are on Debian Like package system. Under Fedora Red hat dist just use a different approach. Code is simple and installation is the key..  Windows use nugets packages Linux you have to install and build Opencv With FFMPEG. Also simple.  It is easy to capture video in OpenCV Video capture  in OpenCV is a really easy task, but for a little bit experienced user.  What is the problem? The problem is the installation of Opencv without recommended dependencies. Just install all basic libs that are recommended on the website. # Basic packa