OpenCV  4.7.0
Open Source Computer Vision
Detecting colorcheckers using neural network

In this tutorial you will learn how to use the neural network to boost up the accuracy of the chart detection algorithm.

Building

When building OpenCV, run the following command to build all the contrib module:

cmake -D OPENCV_EXTRA_MODULES_PATH=<opencv_contrib>/modules/

Or only build the mcc module:

cmake -D OPENCV_EXTRA_MODULES_PATH=<opencv_contrib>/modules/mcc

Or make sure you check the mcc module in the GUI version of CMake: cmake-gui.

Source Code of the sample

You can run the sample code by doing

<path_of_your_opencv_build_directory>/bin/example_mcc_chart_detection_with_network -t=<type_of_chart> -m=<path_to_neural_network> -pb=<path_to_models_pbtxt> -v=<optional_path_to_video_if_not_provided_webcam_will_be_used.mp4> --ci=<optional_camera_id_needed_only_if_video_not_provided> --nc=<optional_maximum_number_of_charts_in_image> --use_gpu <optional_should_gpu_be_used>
``'
* -t=# is the chart type where 0 (Standard), 1 (DigitalSG), 2 (Vinyl)
* --ci=# is the camera ID where 0 (default is the main camera), 1 (secondary camera) etc
* --nc=# By default its values is 1 which means only the best chart will be detected
Example:

Simple run on CPU (GPU wont be used) /home/opencv/build/bin/example_mcc_chart_detection_with_network -t=0 -m=/home/model.pb –pb=/home/model.pbtxt -v=mcc24.mp4

To run on GPU /home/opencv/build/bin/example_mcc_chart_detection_with_network -t=0 -m=/home/model.pb –pb=/home/model.pbtxt -v=mcc24.mp4 –use_gpu

To run on GPU and detect the best 5 charts (Detections can be less than 5 but not more than 5) /home/opencv/build/bin/example_mcc_chart_detection_with_network -t=0 -m=/home/model.pb –pb=/home/model.pbtxt -v=mcc24.mp4 –use_gpu –nc=5 ```

1 #include <opencv2/core.hpp>
2 
3 #include <opencv2/highgui.hpp>
4 #include <opencv2/mcc.hpp>
5 #include <opencv2/dnn.hpp>
6 #include <iostream>
7 
8 using namespace std;
9 using namespace cv;
10 using namespace mcc;
11 
12 const char *about = "Basic chart detection using neural network";
13 const char *keys = {
14  "{ help h usage ? | | show this message }"
15  "{t | 0 | chartType: 0-Standard, 1-DigitalSG, 2-Vinyl, default:0}"
16  "{m | | File path of model, if you don't have the model you can \
17  find the link in the documentation}"
18  "{pb | | File path of pbtxt file, available along with with the model \
19  file }"
20  "{v | | Input from video file, if ommited, input comes from camera }"
21  "{ci | 0 | Camera id if input doesnt come from video (-v) }"
22  "{nc | 1 | Maximum number of charts in the image }"
23  "{use_gpu | | Add this flag if you want to use gpu}"};
24 
25 int main(int argc, char *argv[])
26 {
27  // ----------------------------------------------------------
28  // Scroll down a bit (~50 lines) to find actual relevant code
29  // ----------------------------------------------------------
30 
31  CommandLineParser parser(argc, argv, keys);
32  parser.about(about);
33 
34  if (parser.has("help"))
35  {
36  parser.printMessage();
37  return -1;
38  }
39 
40  int t = parser.get<int>("t");
41 
42  CV_Assert(0 <= t && t <= 2);
43  TYPECHART chartType = TYPECHART(t);
44 
45  string model_path = parser.get<string>("m");
46  string pbtxt_path = parser.get<string>("pb");
47 
48  int camId = parser.get<int>("ci");
49  int nc = parser.get<int>("nc");
50 
51  String video;
52 
53  if (parser.has("v"))
54  video = parser.get<String>("v");
55 
56  bool use_gpu = parser.has("use_gpu");
57 
58  if (!parser.check())
59  {
60  parser.printErrors();
61  return 0;
62  }
63 
64  VideoCapture inputVideo;
65  int waitTime;
66  if (!video.empty())
67  {
68  inputVideo.open(video);
69  waitTime = 10;
70  }
71  else
72  {
73  inputVideo.open(camId);
74  waitTime = 10;
75  }
76 
77  //--------------------------------------------------------------------------
78  //-------------------------Actual Relevant Code-----------------------------
79  //--------------------------------------------------------------------------
80 
81  //load the network
82 
83  cv::dnn::Net net = cv::dnn::readNetFromTensorflow(model_path, pbtxt_path);
84 
85  if (use_gpu)
86  {
89  }
90 
91  Ptr<CCheckerDetector> detector = CCheckerDetector::create();
92  if (!detector->setNet(net))
93  {
94  cout << "Loading Model failed: Aborting" << endl;
95  return 0;
96  }
97 
98  while (inputVideo.grab())
99  {
100  Mat image, imageCopy;
101  inputVideo.retrieve(image);
102 
103  imageCopy = image.clone();
104 
105  // Marker type to detect
106  if (!detector->process(image, chartType, nc, true))
107  {
108  printf("ChartColor not detected \n");
109  }
110  else
111  {
112 
113  // get checker
114  std::vector<Ptr<mcc::CChecker>> checkers = detector->getListColorChecker();
115  for (Ptr<mcc::CChecker> checker : checkers)
116  {
117  // current checker
118 
119  Ptr<CCheckerDraw> cdraw = CCheckerDraw::create(checker);
120  cdraw->draw(image);
121  }
122  }
123 
124  imshow("image result | q or esc to quit", image);
125  imshow("original", imageCopy);
126  char key = (char)waitKey(waitTime);
127  if (key == 27)
128  break;
129  }
130 
131  return 0;
132 }
Definition: dnn.hpp:81
std::shared_ptr< _Tp > Ptr
Definition: cvstd_wrapper.hpp:23
void setPreferableBackend(int backendId)
Ask network to use specific computation backend where it supported.
void setPreferableTarget(int targetId)
Ask network to make computations on specific target device.
void imshow(const String &winname, InputArray mat)
Displays an image in the specified window.
This class allows to create and manipulate comprehensive artificial neural networks.
Definition: dnn.hpp:458
"black box" representation of the file storage associated with a file on disk.
Definition: affine.hpp:51
Designed for command line parsing.
Definition: utility.hpp:817
#define CV_Assert(expr)
Checks a condition at runtime and throws exception if it fails.
Definition: base.hpp:342
Class for video capturing from video files, image sequences or cameras.
Definition: videoio.hpp:714
TYPECHART
enum to hold the type of the checker
Definition: checker_model.hpp:46
CV_NODISCARD_STD Mat clone() const
Creates a full copy of the array and the underlying data.
Net readNetFromTensorflow(const String &model, const String &config=String())
Reads a network model stored in TensorFlow framework&#39;s format.
virtual bool retrieve(OutputArray image, int flag=0)
Decodes and returns the grabbed video frame.
virtual bool open(const String &filename, int apiPreference=CAP_ANY)
Opens a video file or a capturing device or an IP video stream for video capturing.
virtual bool grab()
Grabs the next frame from video file or capturing device.
std::string String
Definition: cvstd.hpp:150
Definition: dnn.hpp:105
n-dimensional dense array class
Definition: mat.hpp:810
int waitKey(int delay=0)
Waits for a pressed key.

Explanation

  1. Set header and namespaces

    #include <opencv2/mcc.hpp>
    using namespace std;
    using namespace cv;
    using namespace mcc;

    If you want you can set the namespace like the code above.

  2. Create the detector object

    Ptr<CCheckerDetector> detector = CCheckerDetector::create();

    This is just to create the object.

  3. Load the model

    cv::dnn::Net net = cv::dnn::readNetFromTensorflow(model_path, pbtxt_path);

    Load the model, here the model supplied with model was trained in tensorflow so we are loading it in tensorflow, but if you have some other model trained in some other framework you can use that also.

  4. **(Optional) Set the dnn backend to CUDA**

    Models run much faster on CUDA, so use CUDA if possible.

  5. Run the detector

    detector->process(image, chartType, max_number_charts_in_image, true);

    If the detector successfully detects atleast one chart, it return true otherwise it returns false. In the above given code we print a failure message if no chart were detected. Otherwise if it were successful, the list of colorcharts is stored inside the detector itself, we will see in the next step on how to extract it. The fourth parameter is for deciding whether to use the net or not.

  6. Get List of ColorCheckers

    std::vector<cv::Ptr<mcc::CChecker>> checkers;
    detector->getListColorChecker(checkers);

    All the colorcheckers that were detected are now stored in the 'checkers' vector.

  7. Draw the colorcheckers back to the image

    for(Ptr<mcc::CChecker> checker : checkers)
    {
    // current checker
    Ptr<CCheckerDraw> cdraw = CCheckerDraw::create(checker);
    cdraw->draw(image);
    }

    Loop through all the checkers one by one and then draw them.