python短视频提取关键帧_提取视频关键帧

"""

Created on Tue Dec 4 16:48:57 2018

keyframes extract tool

this key frame extract algorithm is based on interframe difference.

The principle is very simple

First, we load the video and compute the interframe difference between each frames

Then, we can choose one of these three methods to extract keyframes, which are

all based on the difference method:

1. use the difference order

The first few frames with the largest average interframe difference

are considered to be key frames.

2. use the difference threshold

The frames which the average interframe difference are large than the

threshold are considered to be key frames.

3. use local maximum

The frames which the average interframe difference are local maximum are

considered to be key frames.

It should be noted that smoothing the average difference value before

calculating the local maximum can effectively remove noise to avoid

repeated extraction of frames of similar scenes.

After a few experiment, the third method has a better key frame extraction effect.

The original code comes from the link below, I optimized the code to reduce

unnecessary memory consumption.

https://blog.csdn.net/qq_21997625/article/details/81285096

@author: zyb_as

"""

import cv2

import operator

import subprocess

import numpy as np

# import matplotlib.pyplot as plt

import sys, os

from scipy.signal import argrelextrema

from musecheck import logger_error, logger_info

from musecheck.resource.conf import MUSECHECK_BASE_DIR

try:

import matplotlib.pyplot as plt

except ModuleNotFoundError as e:

logger_error(f'matplotlib，尝试执行pip install matplotlib')

matplotlib_path = os.path.join(MUSECHECK_BASE_DIR, 'libs', 'matplotlib-3.3.2-cp37-cp37m-manylinux1_x86_64.whl')

try:

subprocess.Popen(f'pip install matplotlib')

logger_info(f'success pip install matplotlib_path')

except Exception as e:

logger_error(f'安装依赖matplotlib_path出错，尝试pip install {matplotlib_path}, ErrorInfo:{e}')

cycler_path = os.path.join(MUSECHECK_BASE_DIR, 'libs', 'cycler-0.10.0-py2.py3-none-any.whl')

certifi_path = os.path.join(MUSECHECK_BASE_DIR, 'libs', 'certifi-2020.6.20-py2.py3-none-any.whl')

kiwisolver_path = os.path.join(MUSECHECK_BASE_DIR, 'libs', 'kiwisolver-1.3.1-cp37-cp37m-manylinux1_x86_64.whl')

Pillow_path = os.path.join(MUSECHECK_BASE_DIR, 'libs', 'Pillow-8.0.1-cp37-cp37m-manylinux1_x86_64.whl')

try:

subprocess.Popen(f'pip install {cycler_path}')

subprocess.Popen(f'pip install {certifi_path}')

subprocess.Popen(f'pip install {kiwisolver_path}')

subprocess.Popen(f'pip install {Pillow_path}')

subprocess.Popen(f'pip install {matplotlib_path}')

logger_info(f'success pip install {matplotlib_path}')

except Exception as e:

logger_error(f'安装依赖matplotlib出错，请联系【youngzhang】, ErrorInfo：{e}')

def smooth(x, window_len=13, window='hanning'):

"""smooth the data using a window with requested size.

This method is based on the convolution of a scaled window with the signal.

The signal is prepared by introducing reflected copies of the signal

(with the window size) in both ends so that transient parts are minimized

in the begining and end part of the output signal.

input:

x: the input signal

window_len: the dimension of the smoothing window

window: the type of window from 'flat', 'hanning', 'hamming', 'bartlett', 'blackman'

flat window will produce a moving average smoothing.

output:

the smoothed signal

example:

import numpy as np

t = np.linspace(-2,2,0.1)

x = np.sin(t)+np.random.randn(len(t))*0.1

y = smooth(x)

see also:

numpy.hanning, numpy.hamming, numpy.bartlett, numpy.blackman, numpy.convolve

scipy.signal.lfilter

TODO: the window parameter could be the window itself if an array instead of a string

"""

print(len(x), window_len)

# if x.ndim != 1:

# raise ValueError, "smooth only accepts 1 dimension arrays."

#

# if x.size < window_len:

# raise ValueError, "Input vector needs to be bigger than window size."

#

# if window_len < 3:

# return x

#

# if not window in ['flat', 'hanning', 'hamming', 'bartlett', 'blackman']:

# raise ValueError, "Window is on of 'flat', 'hanning', 'hamming', 'bartlett', 'blackman'"

s = np.r_[2 * x[0] - x[window_len:1:-1],

x, 2 * x[-1] - x[-1:-window_len:-1]]

# print(len(s))

if window == 'flat': # moving average

w = np.ones(window_len, 'd')

else:

w = getattr(np, window)(window_len)

y = np.convolve(w / w.sum(), s, mode='same')

return y[window_len - 1:-window_len + 1]

class Frame:

"""class to hold information about each frame

"""

def __init__(self, id, diff):

self.id = id

self.diff = diff

def __lt__(self, other):

if self.id == other.id:

return self.id < other.id

return self.id < other.id

def __gt__(self, other):

return other.__lt__(self)

def __eq__(self, other):

return self.id == other.id and self.id == other.id

def __ne__(self, other):

return not self.__eq__(other)

def rel_change(a, b):

x = (b - a) / max(a, b)

print(x)

return x

def extract_key_frame(video_path, key_frame_save_path):

# print(sys.executable)

# Setting fixed threshold criteria

USE_THRESH = False

# fixed threshold value

THRESH = 0.8

# Setting fixed threshold criteria

USE_TOP_ORDER = False

# Setting local maxima criteria

USE_LOCAL_MAXIMA = True

# Number of top sorted frames

NUM_TOP_FRAMES = 50

# Video path of the source file

video_path = video_path

# Directory to store the processed frames

save_path = key_frame_save_path

# dir = f'./key_frame_pic/{os.path.basename(videopath).split(".")[0]}/'

# smoothing window size

len_window = int(50)

print("target video :" + video_path)

print("frame save directory: " + save_path)

if not os.path.exists(save_path):

os.makedirs(save_path)

# load video and compute diff between frames

cap = cv2.VideoCapture(str(video_path))

curr_frame = None

prev_frame = None

frame_diffs = []

frames = []

success, frame = cap.read()

i = 0

while (success):

luv = cv2.cvtColor(frame, cv2.COLOR_BGR2LUV)

curr_frame = luv

if curr_frame is not None and prev_frame is not None:

# logic here

diff = cv2.absdiff(curr_frame, prev_frame)

diff_sum = np.sum(diff)

diff_sum_mean = diff_sum / (diff.shape[0] * diff.shape[1])

frame_diffs.append(diff_sum_mean)

frame = Frame(i, diff_sum_mean)

frames.append(frame)

prev_frame = curr_frame

i = i + 1

success, frame = cap.read()

cap.release()

# compute keyframe

keyframe_id_set = set()

if USE_TOP_ORDER:

print("Using Top order")

# sort the list in descending order

frames.sort(key=operator.attrgetter("diff"), reverse=True)

for keyframe in frames[:NUM_TOP_FRAMES]:

keyframe_id_set.add(keyframe.id)

if USE_THRESH:

print("Using Threshold")

for i in range(1, len(frames)):

if (rel_change(np.float(frames[i - 1].diff), np.float(frames[i].diff)) >= THRESH):

keyframe_id_set.add(frames[i].id)

if USE_LOCAL_MAXIMA:

print("Using Local Maxima")

diff_array = np.array(frame_diffs)

sm_diff_array = smooth(diff_array, len_window)

frame_indexes = np.asarray(argrelextrema(sm_diff_array, np.greater))[0]

for i in frame_indexes:

keyframe_id_set.add(frames[i - 1].id)

plt.figure(figsize=(40, 20))

plt.locator_params(tight=100)

plt.stem(sm_diff_array)

plt.savefig(save_path + 'plot.png')

# 要记得close(),否则会内存泄露

plt.close()

# save all keyframes as image

cap = cv2.VideoCapture(str(video_path))

curr_frame = None

keyframes = []

success, frame = cap.read()

idx = 0

key_frame_list = []

while (success):

if idx in keyframe_id_set:

name = str(idx) + ".jpg"

cv2.imwrite(save_path + name, frame)

key_frame_list.append(idx)

keyframe_id_set.remove(idx)

idx = idx + 1

success, frame = cap.read()

cap.release()

return key_frame_list