def load_annotation_file(self, alov_sub_folder, annotation_file):
video_path = os.path.join(self.alov_folder, alov_sub_folder,
annotation_file.split('/')[-1].split('.')[0])
objVideo = video(video_path)
all_frames = glob.glob(os.path.join(video_path, '*.jpg'))
objVideo.all_frames = sorted(all_frames)
with open(annotation_file, 'r') as f:
data = f.read().rstrip().split('\n')
for bb in data:
frame_num, ax, ay, bx, by, cx, cy, dx, dy = bb.split()
frame_num, ax, ay, bx, by, cx, cy, dx, dy = int(
frame_num), float(ax), float(ay), float(bx), float(
by), float(cx), float(cy), float(dx), float(dy)
x1 = min(ax, min(bx, min(cx, dx))) - 1
y1 = min(ay, min(by, min(cy, dy))) - 1
x2 = max(ax, max(bx, max(cx, dx))) - 1
y2 = max(ay, max(by, max(cy, dy))) - 1
bbox = BoundingBox(x1, y1, x2, y2)
objFrame = frame(frame_num - 1, bbox)
objVideo.annotations.append(objFrame)
video_name = video_path.split('/')[-1]
self.alov_videos[video_name] = objVideo
if alov_sub_folder not in self.category.keys():
self.category[alov_sub_folder] = []
self.category[alov_sub_folder].append(self.alov_videos[video_name])
def load_annotation_file(self, vid_sub_folder, annotation_file):
video_path = os.path.join(self.vid_folder, vid_sub_folder,
annotation_file)
objVideo = video(video_path)
all_frames = glob.glob(os.path.join(video_path, '*.JPEG'))
logger.info('{:>4} has {:>3} images'.format(annotation_file,
len(all_frames)))
objVideo.all_frames = sorted(all_frames)
annotation_xml = sorted(
glob.glob(
os.path.join(self.annotations_folder, vid_sub_folder,
annotation_file, '*.xml')))
for frame_num, xml in enumerate(annotation_xml):
root = ET.parse(xml).getroot()
folder = root.find('folder').text
filename = root.find('filename').text
size = root.find('size')
disp_width = int(size.find('width').text)
disp_height = int(size.find('height').text)
# trackid 0 only
for obj in root.findall('object'):
if obj.find('trackid').text == '0':
bbox = obj.find('bndbox')
xmin = int(bbox.find('xmin').text)
xmax = int(bbox.find('xmax').text)
ymin = int(bbox.find('ymin').text)
ymax = int(bbox.find('ymax').text)
bbox = BoundingBox(xmin, ymin, xmax, ymax)
objFrame = frame(frame_num, bbox)
objVideo.annotations.append(objFrame)
video_name = video_path.split('/')[-1]
self.vid_videos[video_name] = objVideo
if vid_sub_folder not in self.category.keys():
self.category[vid_sub_folder] = []
self.category[vid_sub_folder].append(self.vid_videos[video_name])
import numpy as np
import cv2
import video
# Number of frames of the video
count = video.frame()
# Haar cascade
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
for i in xrange(0, count - 1):
img = cv2.imread("frames/frame%d.jpg" % i)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x, y, w, h) in faces:
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 0), 2)
roi_gray = gray[y:y + h, x:x + w]
roi_color = img[y:y + h, x:x + w]
# Save in a folder the image of the face (gray and colour)
cv2.imwrite("fc/f%d.jpg" % i, roi_color)
cv2.imwrite("fg/f%d.jpg" % i, roi_gray)