利用python读取YUV文件 转RGB 8bit/10bit通用

注:本文所指的YUV均为YUV420中的I420格式(最常见的一种),其他格式不能用以下的代码。

位深为8bit时,每个像素占用1字节,对应文件指针的fp.read(1);

位深为10bit时,每个像素占用2字节,对应文件指针的fp.read(2);

然后使用 int.from_bytes() 方法将二进制转换为int型数字。

以下程序可以读8bit或10bit位深的YUV,需要指定从第几帧开始读、一共读多少帧。

它返回三个数组,其shape分别为:Y [frame,W,H] U [frame,W/2,H/2] V [frame,W/2,H/2]

当只读1帧时它返回:Y [W,H] U [W/2,H/2] V [W/2,H/2]

# -*- coding: utf-8 -*-
 
import math
from functools import partial
import numpy as np
import matplotlib.pyplot as plt
 
 
def readyuv420(filename, bitdepth, W, H, startframe, totalframe, show=False):
  # 从第startframe(含)开始读(0-based),共读totalframe帧
 
  uv_H = H // 2
  uv_W = W // 2
 
  if bitdepth == 8:
    Y = np.zeros((totalframe, H, W), np.uint8)
    U = np.zeros((totalframe, uv_H, uv_W), np.uint8)
    V = np.zeros((totalframe, uv_H, uv_W), np.uint8)
  elif bitdepth == 10:
    Y = np.zeros((totalframe, H, W), np.uint16)
    U = np.zeros((totalframe, uv_H, uv_W), np.uint16)
    V = np.zeros((totalframe, uv_H, uv_W), np.uint16)
 
  plt.ion()
 
  bytes2num = partial(int.from_bytes, byteorder='little', signed=False)
 
  bytesPerPixel = math.ceil(bitdepth / 8)
  seekPixels = startframe * H * W * 3 // 2
  fp = open(filename, 'rb')
  fp.seek(bytesPerPixel * seekPixels)
 
  for i in range(totalframe):
 
    for m in range(H):
      for n in range(W):
        if bitdepth == 8:
          pel = bytes2num(fp.read(1))
          Y[i, m, n] = np.uint8(pel)
        elif bitdepth == 10:
          pel = bytes2num(fp.read(2))
          Y[i, m, n] = np.uint16(pel)
 
    for m in range(uv_H):
      for n in range(uv_W):
        if bitdepth == 8:
          pel = bytes2num(fp.read(1))
          U[i, m, n] = np.uint8(pel)
        elif bitdepth == 10:
          pel = bytes2num(fp.read(2))
          U[i, m, n] = np.uint16(pel)
 
    for m in range(uv_H):
      for n in range(uv_W):
        if bitdepth == 8:
          pel = bytes2num(fp.read(1))
          V[i, m, n] = np.uint8(pel)
        elif bitdepth == 10:
          pel = bytes2num(fp.read(2))
          V[i, m, n] = np.uint16(pel)
 
    if show:
      print(i)
      plt.subplot(131)
      plt.imshow(Y[i, :, :], cmap='gray')
      plt.subplot(132)
      plt.imshow(U[i, :, :], cmap='gray')
      plt.subplot(133)
      plt.imshow(V[i, :, :], cmap='gray')
      plt.show()
      plt.pause(1)
      #plt.pause(0.001)
 
  if totalframe==1:
    return Y[0], U[0], V[0]
  else:
    return Y,U,V
 
 
if __name__ == '__main__':
  #y, u, v = readyuv420(r'F:\_commondata\video\176x144 qcif\football_qcif.yuv', 8, 176, 144, 1, 5, True)
  y, u, v = readyuv420(r'F:\_commondata\video\1920x1080 B\RitualDance_1920x1080_60fps_10bit_420.yuv', 10, 1920, 1080, 0, 5, True)
  print(y.shape,u.shape,v.shape)

以下程序将YUV转为RGB(只能读8bit位深的YUV),返回1个数组,其shape为: [frame,W,H,3]

# -*- coding: utf-8 -*-
import cv2
import numpy as np
import matplotlib.pyplot as plt
 
 
def yuv2rgb(yuvfilename, W, H, startframe, totalframe, show=False, out=False):
  # 从第startframe(含)开始读(0-based),共读totalframe帧
  arr = np.zeros((totalframe,H,W,3), np.uint8)
  
  plt.ion()
  with open(yuvfilename, 'rb') as fp:
    seekPixels = startframe * H * W * 3 // 2
    fp.seek(8 * seekPixels) #跳过前startframe帧
    for i in range(totalframe):
      print(i)
      oneframe_I420 = np.zeros((H*3//2,W),np.uint8)
      for j in range(H*3//2):
        for k in range(W):
          oneframe_I420[j,k] = int.from_bytes(fp.read(1), byteorder='little', signed=False)
      oneframe_RGB = cv2.cvtColor(oneframe_I420,cv2.COLOR_YUV2RGB_I420)
      if show:
        plt.imshow(oneframe_RGB)
        plt.show()
        plt.pause(0.001)
      if out:
        outname = yuvfilename[:-4]+'_'+str(startframe+i)+'.png'
        cv2.imwrite(outname,oneframe_RGB[:,:,::-1])
      arr[i] = oneframe_RGB
  return arr
 
if __name__ == '__main__':
  video = yuv2rgb(r'D:\_workspace\akiyo_qcif.yuv', 176, 144, 0, 10, False, True)

用ffmpeg也可以,比如你需要将yuv的第8帧输出成一个png:

ffmpeg -s 176x144 -i akiyo_qcif.yuv -filter:v select="between(n\,8\,8)" out.png

以上这篇利用python读取YUV文件 转RGB 8bit/10bit通用就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持脚本之家。

你可能感兴趣的:(利用python读取YUV文件 转RGB 8bit/10bit通用)