python - 如何使用 ffmpeg gpu 编码将帧从视频保存到内存？

Question

我正在尝试从视频中提取帧并将它们保存到内存 (ram)。 使用 CPU 编码，我没有任何问题:

ffmpeg -i input -s 224x224 -pix_fmt bgr24 -vcodec rawvideo -an -sn -f image2pipe -

但是，当我尝试使用某些 NVIDIA GPU 编码时，我总是得到嘈杂的图像。 我尝试使用不同的命令，但在 Windows 和 Ubuntu 上结果总是一样。

ffmpeg -hwaccel cuda -i 12.mp4 -s 224x224 -f image2pipe - -vcodec rawvideo

在磁盘上保存 JPG，我没有任何问题。

ffmpeg -hwaccel cuvid -c:v h264_cuvid -resize 224x224 -i {input_video} \
     -vf thumbnail_cuda=2,hwdownload,format=nv12 {output_dir}/%d.jpg

我的 python 代码用于测试这些命令:

import cv2
import subprocess as sp
import numpy

IMG_W = 224
IMG_H = 224
input = '12.mp4'

ffmpeg_cmd = [ 'ffmpeg','-i', input,'-s', '224x224','-pix_fmt', 'bgr24',  '-vcodec', 'rawvideo', '-an','-sn', '-f', 'image2pipe', '-']


#ffmpeg_cmd = ['ffmpeg','-hwaccel' ,'cuda' ,'-i' ,'12.mp4','-s', '224x224','-f' , 'image2pipe' ,'-' , '-vcodec' ,'rawvideo']

pipe = sp.Popen(ffmpeg_cmd, stdout = sp.PIPE, bufsize=10)
images = []
encode_param = [int(cv2.IMWRITE_JPEG_QUALITY), 95]
cnt = 0
while True:
    cnt += 1
    raw_image = pipe.stdout.read(IMG_W*IMG_H*3)
    image =  numpy.fromstring(raw_image, dtype='uint8')     # convert read bytes to np
    if image.shape[0] == 0:
        del images
        break   
    else:
        image = image.reshape((IMG_H,IMG_W,3))
        

    cv2.imshow('test',image)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

pipe.stdout.flush()
cv2.destroyAllWindows()

Answer 1

为了加速 H.264 解码，最好选择 -c:v h264_cuvid - 它在 GPU 中使用专用视频硬件。

用GPU-Z监控软件测试，好像-hwaccel cuda也用了专用加速器(同-c:v h264_cuvid)，但我不是当然。

注意:

• NVIDIA CUVID 视频解码加速器不支持所有尺寸和像素格式。

---

问题:

• bufsize=10太小了，最好不要设置bufsize参数，设置bufsize=10。

• 代替 '-f', 'image2pipe'，使用 '-f', 'rawvideo'(我们正在从管道读取原始视频帧，而不是图像 [如 JPEG 或 PNG])。
  我们可以在使用 '-f', 'rawvideo' 时删除 '-vcodec', 'rawvideo'。

• 我们不需要参数 '-s', '224x224'，因为输出大小从输入视频中已知。

更新的 FFmpeg 命令:

ffmpeg_cmd = ['ffmpeg', '-hwaccel', 'cuda', '-c:v', 'h264_cuvid', '-i', input, '-pix_fmt', 'bgr24', '-f', 'rawvideo', '-']

---

为了创建可重现的代码示例，我首先创建一个合成视频文件 'test.mp4'，它将用作输入:

# Build synthetic video file for testing.
################################################################################
sp.run(['ffmpeg', '-y', '-f', 'lavfi', '-i', f'testsrc=size={IMG_W}x{IMG_H}:rate=1',
        '-f', 'lavfi', '-i', 'sine=frequency=300', '-c:v', 'libx264', '-pix_fmt', 'nv12', 
        '-c:a', 'aac', '-ar', '22050', '-t', '50', input])
################################################################################

---

这是一个完整的(可执行的)代码示例:

import cv2
import subprocess as sp
import numpy


IMG_W = 224
IMG_H = 224
input = 'test.mp4'

# Build synthetic video file for testing.
################################################################################
sp.run(['ffmpeg', '-y', '-f', 'lavfi', '-i', f'testsrc=size={IMG_W}x{IMG_H}:rate=1',
        '-f', 'lavfi', '-i', 'sine=frequency=300', '-c:v', 'libx264', '-pix_fmt', 'nv12', 
        '-c:a', 'aac', '-ar', '22050', '-t', '50', input])
################################################################################

# There is no damage using both '-hwaccel cuda' and '-c:v 'h264_cuvid'.
ffmpeg_cmd = ['ffmpeg', '-hwaccel', 'cuda', '-c:v', 'h264_cuvid', '-i', input, '-pix_fmt', 'bgr24', '-f', 'rawvideo', '-']
   
pipe = sp.Popen(ffmpeg_cmd, stdout=sp.PIPE)

cnt = 0
while True:
    cnt += 1
    raw_image = pipe.stdout.read(IMG_W*IMG_H*3)
    image =  numpy.fromstring(raw_image, dtype='uint8')     # convert read bytes to np
    if image.shape[0] == 0:
        break
    else:
        image = image.reshape((IMG_H, IMG_W, 3))
        
    cv2.imshow('test', image)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

pipe.stdout.close()
pipe.wait()
cv2.destroyAllWindows()

---

更新:

生成 JPEG 而不是原始帧:

我找到的用于在内存中构建 JPEG 图像列表的解决方案应用输出流的“手动”解析。

FFmpeg 命令(选择 YUV420 像素格式):

ffmpeg_cmd = ['ffmpeg', '-hwaccel', 'cuda', '-c:v', 'h264_cuvid', '-i', input, '-c:v', 'mjpeg', '-pix_fmt', 'yuvj420p', '-f', 'image2pipe', '-']

JPEG file format在 SOS 负载的 header 中没有长度。
查找 SOS 负载的末尾需要字节扫描，并且使用 Python 实现非常慢。

以下解决方案与大多数用户无关。
我决定发布它，因为它可能与某人相关。

这里是一个代码示例(第一部分构建用于测试的合成视频文件):

import cv2
import subprocess as sp
import numpy as np
import struct


IMG_W = 224
IMG_H = 224
input = 'test.mp4'

# Build synthetic video file for testing.
################################################################################
sp.run(['ffmpeg', '-y', '-f', 'lavfi', '-i', f'testsrc=size={IMG_W}x{IMG_H}:rate=1',
         '-f', 'lavfi', '-i', 'sine=frequency=300', '-c:v', 'libx264', '-pix_fmt', 'nv12',
         '-c:a', 'aac', '-ar', '22050', '-t', '50', input])
################################################################################

def read_from_pipe(p_stdout, n_bytes):
    """ Read n_bytes bytes from p_stdout pipe, and return the read data bytes. """
    data = p_stdout.read(n_bytes)
    while len(data) < n_bytes:
        data += p_stdout.read(n_bytes - len(data))

    return data


ffmpeg_cmd = ['ffmpeg', '-hwaccel', 'cuda', '-c:v', 'h264_cuvid', '-i', input, '-c:v', 'mjpeg', '-pix_fmt', 'yuvj420p', '-f', 'image2pipe', '-']

pipe = sp.Popen(ffmpeg_cmd, stdout=sp.PIPE)

jpg_list = []

cnt = 0
while True:
    if not pipe.poll() is None:
        break

    # https://en.wikipedia.org/wiki/JPEG_File_Interchange_Format
    jpeg_parts = []

    # SOI
    soi = read_from_pipe(pipe.stdout, 2)  # Read Start of Image (FF D8)
    assert soi == b'\xff\xd8', 'Error: first two bytes are not FF D8'
    jpeg_parts.append(soi)

    # JFIF APP0 marker segment
    marker = read_from_pipe(pipe.stdout, 2)  # APP0 marker (FF E0)
    assert marker == b'\xff\xe0', 'Error: APP0 marker is not FF E0'
    jpeg_parts.append(marker)

    xx = 0

    # Keep reading markers and segments until marker is EOI (0xFFD9)
    while xx != 0xD9:  # marker != b'\xff\xd9':
        # Length of segment excluding APP0 marker
        length_of_segment = read_from_pipe(pipe.stdout, 2)
        jpeg_parts.append(length_of_segment)
        length_of_segment = struct.unpack('>H', length_of_segment)[0]  # Unpack to uint16 (big endian)

        segment = read_from_pipe(pipe.stdout, length_of_segment - 2)  # Read the segment (minus 2 bytes because length includes the 2 bytes of length)
        jpeg_parts.append(segment)

        marker = read_from_pipe(pipe.stdout, 2)  # JFXX-APP0 marker (FF E0) or SOF or DHT or COM or SOS or EOI
        jpeg_parts.append(marker)

        if marker == b'\xff\xda':  # SOS marker (0xFFDA)
            # https://stackoverflow.com/questions/26715684/parsing-jpeg-sos-marker
            # Summary of how to find next marker after SOS marker (0xFFDA):
            #
            # Skip first 3 bytes after SOS marker (2 bytes header size + 1 byte number of image components in scan).
            # Search for next FFxx marker (skip every FF00 and range from FFD0 to FFD7 because they are part of scan).
            # *This is summary of comments below post of user3344003 + my knowledge + Table B.1 from https://www.w3.org/Graphics/JPEG/itu-t81.pdf.
            #
            # *Basing on Table B.1 I can also suspect that values FF01 and FF02 through FFBF should also be skipped in point 2 but I am not sure if they cannot appear as part of encoded SOS data.
            first3bytes = read_from_pipe(pipe.stdout, 3)
            jpeg_parts.append(first3bytes)  # Skip first 3 bytes after SOS marker (2 bytes header size + 1 byte number of image components in scan).

            xx = 0

            # Search for next FFxx marker, skip every FF00 and range from FFD0 to FFD7 and FF01 and FF02 through FFBF
            while (xx < 0xBF) or ((xx >= 0xD0) and (xx <= 0xD7)):
                # Search for next FFxx marker
                b = 0
                while b != 0xFF:
                    b = read_from_pipe(pipe.stdout, 1)
                    jpeg_parts.append(b)
                    b = b[0]
            
                xx = read_from_pipe(pipe.stdout, 1)  # Read next byte after FF
                jpeg_parts.append(xx)
                xx = xx[0]

    # Join list parts elements to bytes array, and append the bytes array to jpg_list (convert to NumPy array).
    jpg_list.append(np.frombuffer(b''.join(jpeg_parts), np.uint8))

    cnt += 1


pipe.stdout.close()
pipe.wait()


# Decode and show images for testing
for im in jpg_list:
    image = cv2.imdecode(im, cv2.IMREAD_UNCHANGED)

    cv2.imshow('test', image)
    if cv2.waitKey(100) & 0xFF == ord('q'):
        break

cv2.destroyAllWindows()