如何在 Python 中调整一个小的 OpenCV 视频捕获窗口的大小？

Question

我正在使用 tensorflow 制作剪刀石头布游戏，用户可以通过网络摄像头玩电脑，但网络摄像头图像太小，如下所示：屏幕截图

这是我使用 OpenCV 的片段：

cap = cv2.VideoCapture(0)

prev_move = None

while True:

    ret, frame = cap.read()

    if not ret:

        continue

    # rectangle for user to play

    cv2.rectangle(frame, (100, 100), (500, 500), (255, 255, 255), 2)

    # rectangle for computer to play

    cv2.rectangle(frame, (800, 100), (1200, 500), (255, 255, 255), 2)

    # extract the region of image within the user rectangle

    roi = frame[100:500, 100:500]

    img = cv2.cvtColor(roi, cv2.COLOR_BGR2RGB)

    img = cv2.resize(img, (227, 227))

    # predict the move made

    pred = model.predict(np.array([img]))

    move_code = np.argmax(pred[0])

    user_move_name = mapper(move_code)

    # predict the winner (human vs computer)

    if prev_move != user_move_name:

        if user_move_name != "none":

            computer_move_name = choice(['rock', 'paper', 'scissors'])

            winner = calculate_winner(user_move_name, computer_move_name)

        else:

            computer_move_name = "none"

            winner = "Waiting..."

    prev_move = user_move_name

    # display the information

    font = cv2.FONT_HERSHEY_SIMPLEX

    cv2.putText(frame, "Your Move: " + user_move_name,

                (50, 50), font, 1.2, (255, 255, 255), 2, cv2.LINE_AA)

    cv2.putText(frame, "Computer's Move: " + computer_move_name,

                (750, 50), font, 1.2, (255, 255, 255), 2, cv2.LINE_AA)

    cv2.putText(frame, "Winner: " + winner,

                (400, 600), font, 2, (0, 0, 255), 4, cv2.LINE_AA)

    if computer_move_name != "none":

        icon = cv2.imread(

            "{}.png".format(computer_move_name))

        icon = cv2.resize(icon, (400, 400))

        frame[100:500, 800:1200] = icon

    cv2.imshow("Rock Paper Scissors", frame)

    k = cv2.waitKey(10)

    if k == ord('q'):

        break

cap.release()

cv2.destroyAllWindows()

我的网络摄像头有问题吗？我尝试调整框架大小，但它不起作用。

Answer 1

您可以使用以下方法调整大小：width = 1500height = 1080dim = (width, height)frame = cv2.resize(frame, dim, interpolation=cv2.INTER_AREA)