Convert video frames to features

video_features.py

# Create X, y series
import cv2
import numpy as np
from keras.preprocessing import image
from keras.applications.vgg16 import VGG16
from keras.applications.vgg16 import preprocess_input

class VGGFramePreprocessor():
    
    def __init__(self, vgg_model):
        self.vgg_model = vgg_model
    
    def process(self, frame):
        img_data = cv2.resize(frame,(224,224))
        img_data = np.expand_dims(img_data, axis=0)
        img_data = preprocess_input(img_data)
        x = self.vgg_model.predict(img_data).flatten()
        x = np.expand_dims(x, axis=0)
        return x

def get_video_frames(video_path):
    vidcap = cv2.VideoCapture(video_path)
    success, frame = vidcap.read()
    while success:
        yield frame
        success,frame = vidcap.read()
    vidcap.release()


frame_preprocessor = VGGFramePreprocessor(VGG16(weights='imagenet', include_top=False))
    

# Load movies and transform frames to features
movies = []
X = []
y = []
for video_path in glob.glob('data/*.avi'):
    print('preprocessing', video_path)
    positive = CLASSES[POS_IDX] in video_path
    _X = np.concatenate([frame_preprocessor.process(frame) for frame in get_video_frames(video_path)])
    _y = np.array(_X.shape[0] * [[int(not positive), int(positive)]])
    X.append(_X)
    y.append(_y)

X = np.concatenate(X)
y = np.concatenate(y)
print(X.shape)
print(y.shape)