Select a static ROI on webcam video on python openCV

Question

I need to selec a ROI (region of interest), or work area, on a live video from my webcam and take a snapshot of ONLY this work area or ROI, but I can't found how to do this.

In this page https://www.learnopencv.com/how-to-select-a-bounding-box-roi-in-opencv-cpp-python/ have a code for draw a ROI but only with images, not a live video.

import cv2
cam = cv2.VideoCapture(0)
cam.set(cv2.CAP_PROP_FRAME_WIDTH, 1280)
cam.set(cv2.CAP_PROP_FRAME_HEIGHT, 720)
cv2.namedWindow("test")

img_counter = 0

while True:
    ret, frame = cam.read()
    cv2.imshow("test", frame)
    if not ret:
        break
    k = cv2.waitKey(1)

    if k % 256 == 27:
        # ESC pressed
        print("Escape hit, closing...")
        break
    elif k % 256 == 32:
        # SPACE pressed
        img_name = "opencv_frame_{}.png".format(img_counter)
        cv2.imwrite(img_name, frame)
        print("{} written!".format(img_name))
        img_counter += 1

cam.release()

cv2.destroyAllWindows()

This code take a snapshot with space key but not draw a ROI area. Thanks in advance!

Answer 1

Here's a widget to select static ROIs from a video frame. Essentially the idea is to use cv2.setMouseCallback() and event handlers to detect if the mouse has been clicked or released. For this implementation, you can extract coordinates by holding down the left mouse button and dragging to select the desired ROI. You can reset the ROI using the right mouse button. To use the widget, press c to pause the video and start cropping. Then you are free to select the ROI. Once you have selected your ROI, press c again to crop the desired section. To resume the video, press r.

import cv2

class staticROI(object):
    def __init__(self):
        self.capture = cv2.VideoCapture('fedex.mp4')

        # Bounding box reference points and boolean if we are extracting coordinates
        self.image_coordinates = []
        self.extract = False
        self.selected_ROI = False

        self.update()

    def update(self):
        while True:
            if self.capture.isOpened():
                # Read frame
                (self.status, self.frame) = self.capture.read()
                cv2.imshow('image', self.frame)
                key = cv2.waitKey(2)

                # Crop image
                if key == ord('c'):
                    self.clone = self.frame.copy()
                    cv2.namedWindow('image')
                    cv2.setMouseCallback('image', self.extract_coordinates)
                    while True:
                        key = cv2.waitKey(2)
                        cv2.imshow('image', self.clone)

                        # Crop and display cropped image
                        if key == ord('c'):
                            self.crop_ROI()
                            self.show_cropped_ROI()

                        # Resume video
                        if key == ord('r'):
                            break
                # Close program with keyboard 'q'
                if key == ord('q'):
                    cv2.destroyAllWindows()
                    exit(1)
            else:
                pass

    def extract_coordinates(self, event, x, y, flags, parameters):
        # Record starting (x,y) coordinates on left mouse button click
        if event == cv2.EVENT_LBUTTONDOWN:
            self.image_coordinates = [(x,y)]
            self.extract = True

        # Record ending (x,y) coordintes on left mouse bottom release
        elif event == cv2.EVENT_LBUTTONUP:
            self.image_coordinates.append((x,y))
            self.extract = False

            self.selected_ROI = True

            # Draw rectangle around ROI
            cv2.rectangle(self.clone, self.image_coordinates[0], self.image_coordinates[1], (0,255,0), 2)

        # Clear drawing boxes on right mouse button click
        elif event == cv2.EVENT_RBUTTONDOWN:
            self.clone = self.frame.copy()
            self.selected_ROI = False

    def crop_ROI(self):
        if self.selected_ROI:
            self.cropped_image = self.frame.copy()

            x1 = self.image_coordinates[0][0]
            y1 = self.image_coordinates[0][1]
            x2 = self.image_coordinates[1][0]
            y2 = self.image_coordinates[1][1]

            self.cropped_image = self.cropped_image[y1:y2, x1:x2]

            print('Cropped image: {} {}'.format(self.image_coordinates[0], self.image_coordinates[1]))
        else:
            print('Select ROI to crop before cropping')

    def show_cropped_ROI(self):
        cv2.imshow('cropped image', self.cropped_image)

if __name__ == '__main__':
    static_ROI = staticROI()