File size: 3,906 Bytes
2c966e2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
import os
import cv2
import numpy as np
from tqdm import tqdm
from mtcnn import MTCNN
def normalize_frame(frame, mean, std):
frame = frame / 255.0
mean = np.array(mean).reshape(1, 1, 3)
std = np.array(std).reshape(1, 1, 3)
normalized_frame = (frame - mean) / std
return normalized_frame
def detect_faces_in_video(video_path, output_dir, padding_percentage=0.3,
mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225],
full_detection_interval=10):
os.makedirs(output_dir, exist_ok=True)
detector = MTCNN()
cap = cv2.VideoCapture(video_path)
if not cap.isOpened():
raise Exception(f"Error: Unable to open video file {video_path}")
total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
frame_count = 0
cropped_faces = []
trackers = []
with tqdm(total=total_frames, desc="Extracting faces", unit="frame") as pbar:
while True:
ret, frame = cap.read()
if not ret:
break
if frame is None:
print(f"[WARNING] Empty frame at {frame_count}")
continue
if frame_count % full_detection_interval == 0:
rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
faces = detector.detect_faces(rgb_frame)
trackers = []
for i, face in enumerate(faces):
confidence = face['confidence']
if confidence < 0.85:
continue
x, y, w, h = face['box']
if w < 50 or h < 50:
continue
padding = max(1, int(min(w, h) * padding_percentage))
x1 = max(0, x - padding)
y1 = max(0, y - padding)
x2 = min(rgb_frame.shape[1], x + w + padding)
y2 = min(rgb_frame.shape[0], y + h + padding)
cropped_face = frame[y1:y2, x1:x2]
if cropped_face.size == 0:
continue
resized_cropped_face = cv2.resize(cropped_face, (224, 224))
normalized_face = normalize_frame(resized_cropped_face, mean, std)
face_filename = f"frame_{frame_count:05d}_face_{i}.npy"
face_path = os.path.join(output_dir, face_filename)
np.save(face_path, normalized_face)
cropped_faces.append(face_path)
tracker = cv2.TrackerCSRT_create()
tracker.init(frame, (x, y, w, h))
trackers.append(tracker)
else:
for i, tracker in enumerate(trackers):
success, box = tracker.update(frame)
if success:
x, y, w, h = [int(v) for v in box]
padding = max(1, int(min(w, h) * padding_percentage))
x1 = max(0, x - padding)
y1 = max(0, y - padding)
x2 = min(frame.shape[1], x + w + padding)
y2 = min(frame.shape[0], y + h + padding)
cropped_face = frame[y1:y2, x1:x2]
if cropped_face.size == 0:
continue
resized_cropped_face = cv2.resize(cropped_face, (224, 224))
normalized_face = normalize_frame(resized_cropped_face, mean, std)
face_filename = f"frame_{frame_count:05d}_track_{i}.npy"
face_path = os.path.join(output_dir, face_filename)
np.save(face_path, normalized_face)
cropped_faces.append(face_path)
frame_count += 1
pbar.update(1)
cap.release()
return cropped_faces
|