Gain insights into OpenCV with C++. Delve into image editing, machine learning functions, and practical applications like object detection. Discover real-world projects to elevate your programming skills.

open_cv_cpp.tar.gz

OpenCV

OpenCV-GUI

OpenCV is extensively used in the business world for various applications, including facial recognition, object detection, and image and video manipulation. 

In this course, you'll learn the basics of OpenCV—an open-source machine learning library. You'll begin with an overview of the OpenCV library before moving on to practical applications like viewing images, videos, and webcam input. Next, you'll learn how to edit images with tools like decolorizing, cropping, resizing, and captioning. You'll dive into machine learning functions like edge detection, contour detection, corner detection, and face detection. Finally, you'll work on practical projects like document scanners and object trackers. 

By the end of this course, you’ll have a solid understanding of OpenCV and machine learning with C++. You'll be able to create functional applications using computer vision principles, preparing you for real-world projects. Taking this course will allow you to take your programming skills to the next level.

Learning OpenCV from Scratch with C++


In this object tracker, we draw a tracking box around an object in the first frame of the video, and then that box will track the object. Let’s look at the code and try to understand it.

# Read the video
First, we use the following code to read the video.

```
// Reads the video frame by frame
vid.read(frame);
```

 We read the videos by getting each frame of the video as an image using `VideoCapture()` and continuously looping through it.

```c++
// Capturs the video
cv::VideoCapture vid("/usercode/object_detection_vid.mp4");
```


# Draw a tracking box
The `Mat` object `frame` is used to store the current video frame read from the video stream. The `vid.read(frame)` statement reads a frame from the video stream and stores it in the `frame` object.

The `selectROI()` function is used to select a region of interest in the current video frame. The function displays the frame in a window and allows the user to select a rectangular region by clicking and dragging the mouse. The function returns the selected region as a `Rect2d` object, which is stored in the `roi` variable.


```
cv::Mat frame;
vid.read(frame);
cv::Rect2d roi = cv::selectROI("Tracking", frame);
```
# Create the tracker
We need to create a `Ptr<cv::TrackerMOSSE>` object `tracker` and initialize it with a new instance of the `TrackerMOSSE` class using the `TrackerMOSSE::create()` method. The `Ptr` class is a smart pointer provided by OpenCV that manages the memory of the object it points to.

The `tracker->init(frame, roi)` statement initializes the `TrackerMOSSE` object with the current video `frame` and the region of interest, `roi`, that was selected using `selectROI()`. The `init` method is used to initialize the tracker with the first frame and the region of interest that should be tracked.

```
cv::Ptr<cv::TrackerMOSSE> tracker;
tracker = cv::TrackerMOSSE::create();
tracker->init(frame, roi);
```
# Tracking box following the tracker
Here, we create a loop that reads the video frames, one by one, and updates the object tracker with the new frame.

The `vid.read(frame)` statement reads the next frame from the video stream and stores it in the `frame` object.

The `tracker->update(frame, roi)` statement updates the object tracker with the new frame. If the tracker is able to find the object, the method returns `true` and the code inside the `if` statement is executed. The `rectangle()` function is used to draw a box around the tracked object in the frame image.

The `imshow()` function is used to display the updated frame in a window named `TrackingFinal`.

The `waitKey()` function is used to wait for user input for `1` millisecond. If the user presses the "P" key, the code inside the `if` statement is executed, breaking out of the loop and stopping the video processing.

Review the steps involved in creating an object tracker.

Introduction to C++ OpenCV

Reading Media

Editing Images

Reading and Editing Images with OpenCV

Advanced Editing

Detection

Assessment on Advanced Editing and Detection

Real-Life Projects

Conclusion

Appendix

Solution: Object Tracker