嗨害大家好鴨，我是小熊貓🖤

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？

---

有什么python相關(guān)報錯解答自己不會的、或者源碼資料/模塊安裝/女裝大佬精通技巧 都可以來這里：（https://jq.qq.com/?_wv=1027&k=2Q3YTfym）或者+V：python10010問我

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(yīng)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
安裝遇到報錯，不會安裝看我主頁置頂文章有。

素材工具

我們需要安裝一下 ffmpeg 音視頻轉(zhuǎn)碼工具

代碼解析

導(dǎo)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(zhuǎn)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_nameprint(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 heightv_fps = cap.get(5)v_width = cap.get(3)v_height = cap.get(4)# 設(shè)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] = maskout.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 subprocessdef video2mp3(file_name):outfile_name = file_name.split('.')[0] + '.mp3'cmd = 'ffmpeg -i ' + file_name + ' -f mp3 ' + outfile_nameprint(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 heightv_fps = cap.get(5)v_width = cap.get(3)v_height = cap.get(4)# 設(shè)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] = maskout.write(frame)else:breakdef 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！

歡迎在評論區(qū)討論交流~

今天的文章就是這樣啦~

我是小熊貓，咱下篇文章再見啦(????)

總結(jié)

以上是生活随笔為你收集整理的减轻剪辑工作必备——Python实现让视频自动打码，再也不怕出现少儿不宜的画面了的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。