Python實現(xiàn)視頻自動打碼的示例代碼

更新時間：2022年04月08日 09:36:10 作者：嗨學編程

我們在觀看視頻的時候，有時候會出現(xiàn)一些奇怪的馬賽克，影響我們的觀影體驗，那么這些馬賽克是如何精確的加上去的呢？本文就來為大家詳細講講

序言

我們在觀看視頻的時候，有時候會出現(xiàn)一些奇怪的馬賽克，影響我們的觀影體驗，那么這些馬賽克是如何精確的加上去的呢？

本次我們就來用Python實現(xiàn)對視頻自動打碼！

準備工作

環(huán)境咱們還是使用 Python3.8 和 pycharm2021 即可

實現(xiàn)原理

將視頻分為音頻和畫面；

畫面中出現(xiàn)人臉和目標比對，相應人臉進行打碼；

處理后的視頻添加聲音；

模塊

手動安裝一下 cv2 模塊，pip install opencv-python 安裝

素材工具

我們需要安裝一下 ffmpeg 音視頻轉碼工具

代碼解析

導入需要使用的模塊

import cv2  
import face_recognition  # 人臉識別庫  99.7%    cmake  dlib  face_recognition
import subprocess

將視頻轉為音頻

def video2mp3(file_name):
    """
    :param file_name: 視頻文件路徑
    :return:
    """
    outfile_name = file_name.split('.')[0] + '.mp3'
    cmd = 'ffmpeg -i ' + file_name + ' -f mp3 ' + outfile_name
    print(cmd)
    subprocess.call(cmd, shell=False)

打碼

def mask_video(input_video, output_video, mask_path='mask.jpg'):
    """
    :param input_video: 需打碼的視頻
    :param output_video: 打碼后的視頻
    :param mask_path: 打碼圖片
    :return:
    """
    # 讀取圖片
    mask = cv2.imread(mask_path)
    # 讀取視頻
    cap = cv2.VideoCapture(input_video)
    # 視頻  fps  width  height
    v_fps = cap.get(5)
    v_width = cap.get(3)
    v_height = cap.get(4)

    # 設置寫入視頻參數(shù)  格式MP4
    # 畫面大小
    size = (int(v_width), int(v_height))
    fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')

    # 輸出視頻
    out = cv2.VideoWriter(output_video, fourcc, v_fps, size)

    # 已知人臉
    known_image = face_recognition.load_image_file('tmr.jpg')
    biden_encoding = face_recognition.face_encodings(known_image)[0]

    cap = cv2.VideoCapture(input_video)

    while (cap.isOpened()):
        ret, frame = cap.read()
        if ret:
            # 檢測人臉
            # 人臉區(qū)域
            face_locations = face_recognition.face_locations(frame)

            for (top_right_y, top_right_x, left_bottom_y, left_bottom_x) in face_locations:
                print((top_right_y, top_right_x, left_bottom_y, left_bottom_x))
                unknown_image = frame[top_right_y - 50:left_bottom_y + 50, left_bottom_x - 50:top_right_x + 50]
                if face_recognition.face_encodings(unknown_image) != []:
                    unknown_encoding = face_recognition.face_encodings(unknown_image)[0]

                    # 對比人臉
                    results = face_recognition.compare_faces([biden_encoding], unknown_encoding)
                    # [True]
                    # 貼圖
                    if results == [True]:
                        mask = cv2.resize(mask, (top_right_x - left_bottom_x, left_bottom_y - top_right_y))
                        frame[top_right_y:left_bottom_y, left_bottom_x:top_right_x] = mask
            out.write(frame)


        else:
            break

音頻添加到畫面

def video_add_mp3(file_name, mp3_file):
    """
    :param file_name: 視頻畫面文件
    :param mp3_file:  視頻音頻文件
    :return:
    """
    outfile_name = file_name.split('.')[0] + '-f.mp4'
    subprocess.call('ffmpeg -i ' + file_name + ' -i ' + mp3_file + ' -strict -2 -f mp4 ' + outfile_name, shell=False)

完整代碼

import cv2 
import face_recognition  # 人臉識別庫  99.7%    cmake  dlib  face_recognition
import subprocess

def video2mp3(file_name):

    outfile_name = file_name.split('.')[0] + '.mp3'
    cmd = 'ffmpeg -i ' + file_name + ' -f mp3 ' + outfile_name
    print(cmd)
    subprocess.call(cmd, shell=False)


def mask_video(input_video, output_video, mask_path='mask.jpg'):

    # 讀取圖片
    mask = cv2.imread(mask_path)
    # 讀取視頻
    cap = cv2.VideoCapture(input_video)
    # 視頻  fps  width  height
    v_fps = cap.get(5)
    v_width = cap.get(3)
    v_height = cap.get(4)

    # 設置寫入視頻參數(shù)  格式MP4
    # 畫面大小
    size = (int(v_width), int(v_height))
    fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')

    # 輸出視頻
    out = cv2.VideoWriter(output_video, fourcc, v_fps, size)

    # 已知人臉
    known_image = face_recognition.load_image_file('tmr.jpg')
    biden_encoding = face_recognition.face_encodings(known_image)[0]

    cap = cv2.VideoCapture(input_video)

    while (cap.isOpened()):
        ret, frame = cap.read()
        if ret:
            # 檢測人臉
            # 人臉區(qū)域
            face_locations = face_recognition.face_locations(frame)

            for (top_right_y, top_right_x, left_bottom_y, left_bottom_x) in face_locations:
                print((top_right_y, top_right_x, left_bottom_y, left_bottom_x))
                unknown_image = frame[top_right_y - 50:left_bottom_y + 50, left_bottom_x - 50:top_right_x + 50]
                if face_recognition.face_encodings(unknown_image) != []:
                    unknown_encoding = face_recognition.face_encodings(unknown_image)[0]

                    # 對比人臉
                    results = face_recognition.compare_faces([biden_encoding], unknown_encoding)
                    # [True]
                    # 貼圖
                    if results == [True]:
                        mask = cv2.resize(mask, (top_right_x - left_bottom_x, left_bottom_y - top_right_y))
                        frame[top_right_y:left_bottom_y, left_bottom_x:top_right_x] = mask
            out.write(frame)


        else:
            break


def video_add_mp3(file_name, mp3_file):

    outfile_name = file_name.split('.')[0] + '-f.mp4'
    subprocess.call('ffmpeg -i ' + file_name + ' -i ' + mp3_file + ' -strict -2 -f mp4 ' + outfile_name, shell=False)


if __name__ == '__main__':
    # 1.
    video2mp3('cut.mp4')
    # 2.
    mask_video(input_video='cut.mp4',output_video='output.mp4')
    # 3.
    video_add_mp3(file_name='output.mp4',mp3_file='cut.mp3')

兄弟們，快去試試吧！

到此這篇關于Python實現(xiàn)視頻自動打碼的示例代碼的文章就介紹到這了,更多相關Python視頻打碼內(nèi)容請搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關文章希望大家以后多多支持腳本之家！

您可能感興趣的文章: