def assign_tags(video_id):
import django
from PIL import Image
sys.path.append(os.path.dirname(__file__))
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "dva.settings")
django.setup()
from django.conf import settings
from dvaapp.models import Video,Frame,Region
from dvalib import annotator
from dvaapp.operations.video_processing import WVideo, WFrame
dv = Video.objects.get(id=video_id)
frames = Frame.objects.all().filter(video=dv)
v = WVideo(dvideo=dv, media_dir=settings.MEDIA_ROOT)
wframes = {df.pk: WFrame(video=v, frame_index=df.frame_index, primary_key=df.pk) for df in frames}
algorithm = annotator.OpenImagesAnnotator()
logging.info("starting annotation {}".format(algorithm.name))
for k,f in wframes.items():
tags = algorithm.apply(f.local_path())
a = Region()
a.region_type = Region.ANNOTATION
a.frame_id = k
a.video_id = video_id
a.object_name = "OpenImagesTag"
a.metadata_text = " ".join([t for t,v in tags.iteritems() if v > 0.1])
a.metadata_json = json.dumps({t:100.0*v for t,v in tags.iteritems() if v > 0.1})
a.full_frame = True
a.save()
print a.metadata_text
def perform_face_indexing(video_id):
from dvaapp.models import Region,Frame,Video,IndexEntries
from dvalib import indexer,detector
from dvaapp.operations.video_processing import WFrame,WVideo
from django.conf import settings
from scipy import misc
face_indexer = indexer.FacenetIndexer()
dv = Video.objects.get(id=video_id)
video = WVideo(dv, settings.MEDIA_ROOT)
frames = Frame.objects.all().filter(video=dv)
wframes = [WFrame(video=video, frame_index=df.frame_index, primary_key=df.pk) for df in frames]
input_paths = {f.local_path(): f.primary_key for f in wframes}
faces_dir = '{}/{}/detections'.format(settings.MEDIA_ROOT, video_id)
indexes_dir = '{}/{}/indexes'.format(settings.MEDIA_ROOT, video_id)
face_detector = detector.FaceDetector()
aligned_paths = face_detector.detect(wframes)
logging.info(len(aligned_paths))
faces = []
faces_to_pk = {}
count = 0
for path, v in aligned_paths.iteritems():
for scaled_img, bb in v:
d = Region()
d.region_type = Region.DETECTION
d.video = dv
d.confidence = 100.0
d.frame_id = input_paths[path]
d.object_name = "mtcnn_face"
left, top, right, bottom = bb[0], bb[1], bb[2], bb[3]
d.y = top
d.x = left
d.w = right - left
d.h = bottom - top
d.save()
face_path = '{}/{}.jpg'.format(faces_dir, d.pk)
output_filename = os.path.join(faces_dir, face_path)
misc.imsave(output_filename, scaled_img)
faces.append(face_path)
faces_to_pk[face_path] = d.pk
count += 1
dv.refresh_from_db()
dv.detections = dv.detections + count
dv.save()
path_count, emb_array, entries, feat_fname, entries_fname = face_indexer.index_faces(faces, faces_to_pk,
indexes_dir, video_id)
i = IndexEntries()
i.video = dv
i.count = len(entries)
i.contains_frames = False
i.contains_detections = True
i.detection_name = "Face"
i.algorithm = 'facenet'
i.entries_file_name = entries_fname.split('/')[-1]
i.features_file_name = feat_fname.split('/')[-1]
i.save()
def ssd_detect(video_id):
"""
This is a HACK since Tensorflow is absolutely atrocious in allocating and freeing up memory.
Once a process / session is allocated a memory it cannot be forced to clear it up.
As a result this code gets called via a subprocess which clears memory when it exits.
:param video_id:
:return:
"""
import django
from PIL import Image
sys.path.append(os.path.dirname(__file__))
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "dva.settings")
django.setup()
from django.conf import settings
from dvaapp.models import Video,Region,Frame
from dvalib import detector
from dvaapp.operations.video_processing import WVideo,WFrame
dv = Video.objects.get(id=video_id)
frames = Frame.objects.all().filter(video=dv)
v = WVideo(dvideo=dv, media_dir=settings.MEDIA_ROOT)
wframes = {df.pk: WFrame(video=v, frame_index=df.frame_index, primary_key=df.pk) for df in frames}
detection_count = 0
algorithm = detector.SSDetector()
logging.info("starting detection {}".format(algorithm.name))
frame_detections = algorithm.detect(wframes.values())
for frame_pk,detections in frame_detections.iteritems():
for d in detections:
dd = Region()
dd.region_type = Region.DETECTION
dd.video = dv
dd.frame_id = frame_pk
dd.object_name = d['name']
dd.confidence = d['confidence']
dd.x = d['left']
dd.y = d['top']
dd.w = d['right'] - d['left']
dd.h = d['bot'] - d['top']
dd.save()
img = Image.open(wframes[frame_pk].local_path())
img2 = img.crop((d['left'], d['top'], d['right'], d['bot']))
img2.save("{}/{}/detections/{}.jpg".format(settings.MEDIA_ROOT, video_id, dd.pk))
detection_count += 1
dv.refresh_from_db()
dv.detections = dv.detections + detection_count
dv.save()