大家好,我擅长使用PyAudio库开发项目,也使用网络摄像头捕获视频,当时我设法将视频和音频记录在两个单独的文件中,但是当用户暂停时出现了问题录制,然后继续该过程,则视频存储没有问题,但仅录制音频,直到发出暂停信号为止。

虽然用户未同时将音频文件和视频进行视频匹配,但我的问题是如何暂停音频记录然后恢复它,希望有人能帮助我附加工作代码

import cv2
import numpy as np
from datetime import datetime
import gtk
import keyboard

import pyaudio
import wave
import sys

flagrecord=True
chunk = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100


def show_webcam(flagrecord):

    cam = cv2.VideoCapture(0)
    fourcc = cv2.VideoWriter_fourcc(*'XVID')
    frame_width = int(cam.get(3))
    frame_height = int(cam.get(4))
    FONT = cv2.FONT_HERSHEY_PLAIN
    filename = datetime.now().strftime("%Y-%m-%d_%H.%M.%S") + ".avi"
    filenamea = datetime.now().strftime("%Y-%m-%d_%H.%M.%S")

    p = pyaudio.PyAudio()
    stream = p.open(format = FORMAT,
                    channels = CHANNELS,
                    rate = RATE,
                    input = True,
                    frames_per_buffer = chunk)
    all = []

    out = cv2.VideoWriter(filename,fourcc, 30, (frame_width,frame_height))

    while True:

        ret_val, img = cam.read()
        title = datetime.now().strftime("%Y-%m-%d*%H:%M:%S")

        if flagrecord:

            img = cv2.flip(img,1)
            cv2.putText(img, "REC", (40,40), FONT, 3 , (0,0,255), 2)
            cv2.circle(img, (20,20), 10 , (0,0,255), -1)
            cv2.rectangle(img, (30,430),(600,480),(0,0,0), -1)
            cv2.putText(img, title, (40,470), FONT, 3 , (255,255,255), 2)
            cv2.imshow('Grabacion de Audiencias', img)
            out.write(img)

            stream.start_stream()
            data = stream.read(chunk)
            all.append(data)

        else:

            img = cv2.flip(img,1)
            cv2.putText(img, "PAUSE", (40,40), FONT, 3 , (255,0,0), 2)
            cv2.circle(img, (20,20), 10 , (255,0,0), -1)
            cv2.rectangle(img, (50,430),(570,480),(0,0,0), -1)
            cv2.putText(img, "Audiencias En Pausa", (60,470), FONT, 3 , (255,255,255), 2)
            cv2.imshow('Grabacion de Audiencias', img)
            stream.stop_stream()

        if cv2.waitKey(1) == 27:
            break
        if keyboard.is_pressed('p'):
            flagrecord=False
        if keyboard.is_pressed('c'):
            flagrecord=True
        if keyboard.is_pressed('q'):
            break

    cam.release()
    out.release()
    cv2.destroyAllWindows()

    data = ''.join(all)
    wf = wave.open(filenamea, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(data)
    wf.close()


def main():
    show_webcam(mirror=True)


if __name__ == '__main__':
    main()

最佳答案

大家好,我设法暂停音频并继续播放视频,我有2秒的延迟,但我认为这是改善框架附件的问题,解决方案的代码

完整的代码

import cv2
import numpy as np
from datetime import datetime
import gtk
import keyboard

import pyaudio
import wave
import sys

flagrecord=True
#chunk = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100
ropen=True
chunk = int(RATE/20)


def show_webcam(flagrecord):

    cam = cv2.VideoCapture(0)
    fourcc = cv2.VideoWriter_fourcc(*'XVID')
    frame_width = int(cam.get(3))
    frame_height = int(cam.get(4))
    FONT = cv2.FONT_HERSHEY_PLAIN
    filename = datetime.now().strftime("%Y-%m-%d_%H.%M.%S") + ".avi"
    filenamea = datetime.now().strftime("%Y-%m-%d_%H.%M.%S")


    p = pyaudio.PyAudio()
    stream = p.open(format = FORMAT,
                    channels = CHANNELS,
                    rate = RATE,
                    input = True,
                    frames_per_buffer = chunk)

    out = cv2.VideoWriter(filename,fourcc, 20, (frame_width,frame_height))

    all = []
    aux = []
    stream.start_stream()

    flagaudio=False

    while True:

        ret_val, img = cam.read()
        title = datetime.now().strftime("%Y-%m-%d*%H:%M:%S")

        if flagrecord:

            img = cv2.flip(img,1)
            cv2.putText(img, "REC", (40,40), FONT, 3 , (0,0,255), 3)
            cv2.circle(img, (20,20), 10 , (0,0,255), -1)
            cv2.rectangle(img, (30,430),(600,480),(0,0,0), -1)
            cv2.putText(img, title, (40,470), FONT, 3 , (255,255,255), 2)
            cv2.imshow('Grabacion de Audiencias', img)
            data = stream.read(chunk)
            aux.append(data)
            out.write(img)

        else:

            img = cv2.flip(img,1)
            cv2.putText(img, "PAUSE", (40,40), FONT, 3 , (255,0,0), 3)
            cv2.circle(img, (20,20), 10 , (255,0,0), -1)
            cv2.rectangle(img, (50,430),(570,480),(0,0,0), -1)
            cv2.putText(img, "Audiencias En Pausa", (60,470), FONT, 3 , (255,0,0), 2)
            cv2.imshow('Grabacion de Audiencias', img)

            if flagaudio:
               all+=aux
               del  aux[:]
               data= 0
               stream.stop_stream()
            else:
               pass


        q=cv2.waitKey(1)
        if q == 27:
            break
        if q == ord('p'):
            flagrecord=False
            flagaudio = True
        if q == ord('c'):
            flagrecord=True
            flagaudio=False
            stream.start_stream()
        if q == ord('q'):
            break

    cam.release()
    out.release()
    cv2.destroyAllWindows()

    stream.close()
    p.terminate()
    all+=aux
    data = ''.join(all)
    wf = wave.open(filenamea, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(data)
    wf.close()




def main():
    show_webcam(mirror=True)


if __name__ == '__main__':
    main()


第一步

flagrecord=True
#chunk = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100
ropen=True
chunk = int(RATE/20)


可变块必须划分为RATE / 20,其中20是帧数,因为我们将连续记录并且时间没有限制

我在这篇文章中找到了这个解决方案

Continuesly streaming audio signal real time infinitely, Python

第二步

all = []
aux = []
stream.start_stream()
flagaudio=False


我们创建一个lita aux start stream.start_stream()并创建以false开头的变量flagaudio = False,这样它就不会在第一个周期内进入

第三步

if flagrecord:

            img = cv2.flip(img,1)
            cv2.putText(img, "REC", (40,40), FONT, 3 , (0,0,255), 3)
            cv2.circle(img, (20,20), 10 , (0,0,255), -1)
            cv2.rectangle(img, (30,430),(600,480),(0,0,0), -1)
            cv2.putText(img, title, (40,470), FONT, 3 , (255,255,255), 2)
            cv2.imshow('Grabacion de Audiencias', img)
            data = stream.read(chunk)
            aux.append(data)
            out.write(img)

        else:

            img = cv2.flip(img,1)
            cv2.putText(img, "PAUSE", (40,40), FONT, 3 , (255,0,0), 3)
            cv2.circle(img, (20,20), 10 , (255,0,0), -1)
            cv2.rectangle(img, (50,430),(570,480),(0,0,0), -1)
            cv2.putText(img, "Audiencias En Pausa", (60,470), FONT, 3 , (255,0,0), 2)
            cv2.imshow('Grabacion de Audiencias', img)

            if flagaudio:
               all+=aux
               del  aux[:]
               data= 0
               stream.stop_stream()
            else:
               pass


在flagrecord内,如果视频变为false时暂停了视频,则放置条件以询问flagaudio变量是否为true,如果这是列表列表全部采用aux的值,则删除列表,以便在下一个周期为了安全起见,它采用音频的新值。据说数据变量的值为0并使用stream.stop_stream()我们停止音频的记录

第四步

q=cv2.waitKey(1)
        if q == 27:
            break
        if q == ord('p'):
            flagrecord=False
            flagaudio = True
        if q == ord('c'):
            flagrecord=True
            flagaudio=False
            stream.start_stream()
        if q == ord('q'):
            break


通过使用q = cv2.waitKey(1),我们控制暂停顺序(字母p),连续录制(字母c)音频和视频以及退出(字母q),在每种顺序中,我们指示创建的变量标志,因此他们允许进入或不允许进入控制条件之一

结束

cam.release()
    out.release()
    cv2.destroyAllWindows()

    stream.close()
    p.terminate()
    all+=aux
    data = ''.join(all)
    wf = wave.open(filenamea, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(p.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(data)
    wf.close()


我们完成了视频和音频的录制过程,并关闭了网络摄像头。

目前,只有三秒钟的音频丢失给了我,但是暂停和继续录制的主要工作是正确的,我认为我的失败在于帧和循环的控制。

希望我的解决方案能对您有所帮助,并给出解释。

关于python - 使用Pyaudio暂停录音,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/56159669/

10-15 11:50