我想在录音中显示鼠标指针

Question

我正在制作一个记录桌面屏幕的屏幕录像机。但是当我录制屏幕时，鼠标指针（光标）在录制中不可见。 那么有什么方法可以在我的录音中显示鼠标指针。 这是我的代码..

import cv2
import numpy as np
import pyautogui
import datetime
date=datetime.datetime.now()

SCREEN_SIZE = (1366, 768)
framerate=12

fourcc = cv2.VideoWriter_fourcc(*'XVID')
filename='E:/project/videos/rec_%s%s%s%s%s%s.avi' %(date.year,date.month,date.day,date.hour,date.minute,date.second)

out = cv2.VideoWriter(filename, fourcc,framerate, SCREEN_SIZE)

while True:

    img = pyautogui.screenshot()

    frame = np.array(img)

    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

    out.write(frame)

    cv2.imshow('screenshot', frame)

    if cv2.waitKey(1) == ord("q"):
        break

cv2.destroyAllWindows()
out.release()

Answer 1

我认为这种方法是不可能的 - 但我总是很高兴得到纠正并学到新的东西。我知道一些解决方法。

首先是继续使用pyautogui 并调用其mouseposition() 函数并将您自己的合成鼠标指针粘贴/绘制到抓斗上。我使用 OpenCV 的 fillPoly() 函数做到了这一点：

#!/usr/bin/env python3

import cv2
import numpy as np
import pyautogui
import datetime

# X and Y coordinates of mouse pointer
Xs = [0,8,6,14,12,4,2,0]
Ys = [0,2,4,12,14,6,8,0]

while True:

    img = pyautogui.screenshot()
    mouseX,mouseY = pyautogui.position()
    mouseX *= 2
    mouseY *= 2

    frame = np.array(img)
    frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)

    # Synthesize mouse pointer
    Xthis = [4*x+mouseX for x in Xs]
    Ythis = [4*y+mouseY for y in Ys]
    points = list(zip(Xthis,Ythis))
    points = np.array(points, 'int32')
    cv2.fillPoly(frame,[points],color=[255,255,255])

    # Make it a bit smaller for display
    frame = cv2.resize(frame,(960,540))

    cv2.imshow('Title', frame)
    if cv2.waitKey(1) == ord("q"):
        break

cv2.destroyAllWindows()
out.release()

---

第二种是使用ffmpeg，它可以捕获鼠标——你可以运行ffmpeg来代替你当前的应用程序，或者通过管道将ffmpeg的输出通过管道传输到你的应用程序中并继续处理它就像你现在一样。可能看起来像这样：

#!/usr/bin/env python3

# ffmpeg -y -pix_fmt bgr0 -f avfoundation -r 20 -t 10 -i 1 -vf scale=w=3840:h=2160 -f rawvideo /dev/null

import sys
import cv2
import time
import subprocess
import numpy as np

w,h = 3840, 2160

def ffmpegGrab():
    """Generator to read frames from ffmpeg subprocess"""
    cmd = [
        'ffmpeg',
        '-pix_fmt', 'bgr0',
        '-f', 'avfoundation',
        '-capture_cursor', '1',
        '-capture_mouse_clicks', '1',
        '-r', '20',
        '-i', '1',
        '-vf','scale=w=3840:h=2160',
        '-f', 'rawvideo',
        'pipe:1'
    ]
    proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)

    while True:
        frame = proc.stdout.read(w*h*4)
        yield np.frombuffer(frame, dtype=np.uint8).reshape((h,w,4))

# Get frame generator
gen = ffmpegGrab()

# Get start time
start = time.time()

# Read video frames from ffmpeg in loop
nFrames = 0
while True:
    # Read next frame from ffmpeg
    frame = next(gen)
    nFrames += 1
    frame = cv2.resize(frame,(960,540))

    cv2.imshow('screenshot', frame)

    if cv2.waitKey(1) == ord("q"):
        break

    fps = nFrames/(time.time()-start)
    print(f'FPS: {fps}')


cv2.destroyAllWindows()
out.release()

请注意，pyautogui 在我的 Mac 上捕获一帧大约需要 600 毫秒，而上面的 ffmpeg 可以达到大约 20fps，即每帧 50 毫秒。

关键字：Python。图像处理、ffmpeg、pyautogui、屏幕抓取、屏幕捕获、屏幕抓取、屏幕捕获、fps。速度，素数。