def is_scene_separable(diff,fps,program_mode,check_mode,img1,img2):
if diff>1: return True
DIST_TRESH = None
TIMEDIFF_TRESH = None
DISTANCE_TRESH_CHECK_SIFT = None
if program_mode == 'scenes':
DIST_TRESH = settings.CLUSTER_DISTANCE_TRESHOLD_MODE_SCENECUT
TIMEDIFF_TRESH = settings.TIMEDIFF_TRESH_MODE_SCENECUT
DISTANCE_TRESH_CHECK_SIFT = settings.CLUSTER_DISTANCE_TRESHOLD_MODE_SCENECUT_CHECK_SIFT
elif program_mode == 'joined':
DIST_TRESH = settings.CLUSTER_DISTANCE_TRESHOLD_MODE_JOINCUT
TIMEDIFF_TRESH = settings.TIMEDIFF_TRESH_MODE_JOINCUT
DISTANCE_TRESH_CHECK_SIFT = settings.CLUSTER_DISTANCE_TRESHOLD_MODE_JOINCUT_CHECK_SIFT
results = []
if 'time_diff' in check_mode:
time_diff = frame_diff_to_milisecs(diff,fps)
if time_diff>(float(TIMEDIFF_TRESH)*1000.0):
results.append(True)
else:
results.append(False)
was_separated_by_dist = False
if 'dist' in check_mode:
dist = img1.get_distance(img2,from_object=True)
# print 'img1',img1.get_only_num(),'img2',img2.get_only_num(),'dist',dist,'DIST_TRESH',DIST_TRESH
if dist > DIST_TRESH:
was_separated_by_dist = True
results.append(True)
else:
results.append(False)
if 'sift' in check_mode and img1 and img2:
if not was_separated_by_dist:
dist = img1.get_distance(img2,from_object=True)
if dist > DISTANCE_TRESH_CHECK_SIFT:
img1 = prepare_img_for_sift(img1)
img2 = prepare_img_for_sift(img2)
loc_desc1 = (img1.loc, img1.desc)
loc_desc2 = (img2.loc, img2.desc)
im1, im2, mscores,qom,mpercent = get_kpm(loc_desc1, loc_desc2, mode='only_match')
# print 'img1',img1.get_only_num(),'img2',img2.get_only_num(),'qom',qom,'QOM_MINIMUM_SCENECUT',settings.QOM_MINIMUM_SCENECUT
if qom < settings.QOM_MINIMUM_SCENECUT:
results.append(True)
else:
results.append(False)
if 'AND' in check_mode:
if False in results: return False
else: return True
if 'OR' in check_mode:
if True in results: return True
else: return False
def SIFT_matching(self,objects_num,verbose):
########### SIFT
# minden kepet osszehasonlitok a settingsben beallitott mennyiseguvel/modon..
if verbose:print '\nSIFT reclustering..'
total_attempts = objects_num
# objektum egyezesek keresese
if verbose:print '\nSearching for SIFT matchings...'
LS = settings.LESS_MATCHES_ATTEMPT_SOURCE
LC = settings.LESS_MATCHES_ATTEMPT_COMPARED
S=1
C=1
if LS>1: S = int(math.ceil(1.0*total_attempts/(1.0*LS)))
else: S = total_attempts
if LC>1: C = int(math.ceil(1.0*(total_attempts)/(1.0*LC)))
else: C = total_attempts
if LS<2: LS = 0
if LC<2: LC = 0
total_attempts = (S*(C-1))/2
co = 0
# egyelore mindet mindennel (kiveve magaval)
# lehetne maskepp, pl mindet csak ref pointokkal
matches_num = 0
for counter_source_cluster, cluster in enumerate(self.clusters):
for counter_source, source in enumerate(cluster):
if (LS==0 or (LS!=0 and counter_source % LS == 0)):
for counter_compared_cluster, cluster2 in enumerate(self.clusters):
for counter_compared, compared in enumerate(cluster2):
if source.get_only_filename() != compared.get_only_filename():
if (LC==0 or (LC!=0 and counter_compared % LC == 0)):
# ha meg ez a source file nem volt osszehasonlitva a compareddel
# k*(k-1)/2 osszehasonlitas, teljes graf. odavissza nem hasonlitok...kicsi ertelme lehetne SIFT miatt talan,
# de igy fele annyi futasi ido
if not source.get_only_filename() in compared.was_matched_with:
co += 1
print '\n(', co, 'of approx.', total_attempts, ') matching attempt'
loc_desc1 = (source.loc, source.desc)
loc_desc2 = (compared.loc, compared.desc)
im1, im2, mscores,qom,mpercent = get_kpm(loc_desc1, loc_desc2, mode='only_match')
if qom > settings.QOM_minimum:
if verbose: print 'matched images:', source.get_only_filename(), '<->', compared.get_only_filename()
matches_num += 1
if source.matching_qom:
if source.matching_qom < qom:
if verbose: print 'Better QOM image match found'
source.matched = compared
source.matching_qom = qom
else:
source.matched = compared
source.matching_qom = qom
if source.matched and (source.matched.get_only_filename() == compared.get_only_filename()):
if source.matching_qom <= qom:
if not source.matched in cluster:
# mikor rakjuk at masik clusterbe?:
'''
dist_fromClusterRefpoint = source.get_distance(self.get_ref_point(cluster))
dist_toClusterRefpoint = source.get_distance(self.get_ref_point(cluster2))
'''
# print cluster[0].get_only_filename(),dist_fromClusterRefpoint,cluster2[0].get_only_filename(),dist_toClusterRefpoint
'''if dist_fromClusterRefpoint > dist_toClusterRefpoint:'''
if verbose: print "* Image flagged to move"
source.flag_move_from_clusternum = counter_source_cluster
source.flag_move_to_clusternum = counter_compared_cluster
source.was_matched_with.append(compared.get_only_filename())
# reclustering
# moving flagged objects to the right cluster
moved = 0
for counter_cluster, cluster in enumerate(self.clusters):
for counter_image, image in enumerate(cluster):
if image.flag_move_to_clusternum and (image.flag_move_to_clusternum != counter_cluster):
moved += 1
# TODO: melyiket rakjam melyikbe? mi alapjan? cluster meretek? tav a centroidtol?
# ha 1 marad csak a clusterben, azt is inkabb elrakjam?
# 1 meret clusterek a legnagyobb QOMeshez at?
img_to_move = cluster.pop(counter_image)
self.clusters[image.flag_move_to_clusternum].append(img_to_move)
if verbose: print '\n\nMoving', moved, 'images to other clusters done'
if verbose:print 'Found SIFT matchings SUM:', matches_num
if verbose:print '\nSearching for SIFT matchings done'
if verbose:print 'SIFT reclustering ended\n'
def are_scenes_joinable(diff,fps,dist,program_mode,check_mode,img1=None,img2=None, length_diff=None,similar_check=False):
# h nem-e lognak egymasba
if diff > 0:
DIST_TRESH = None
TIMEDIFF_TRESH = None
DISTANCE_TRESH_CHECK_SIFT = None
if program_mode == 'scenes':
DIST_TRESH = settings.CLUSTER_DISTANCE_TRESHOLD_MODE_SCENECUT
if similar_check:
DIST_TRESH = settings.CLUSTER_DISTANCE_TRESHOLD_SIMILAR_CHECK
TIMEDIFF_TRESH = settings.TIMEDIFF_TRESH_MODE_SCENECUT
LENGTH_TRESH = settings.LENGTH_TRESH_MODE_SCENECUT
DISTANCE_TRESH_CHECK_SIFT = settings.CLUSTER_DISTANCE_TRESHOLD_MODE_SCENECUT_CHECK_SIFT
elif program_mode == 'joined':
DIST_TRESH = settings.CLUSTER_DISTANCE_TRESHOLD_MODE_JOINCUT
if similar_check:
DIST_TRESH = settings.CLUSTER_DISTANCE_TRESHOLD_SIMILAR_CHECK
TIMEDIFF_TRESH = settings.TIMEDIFF_TRESH_MODE_JOINCUT
LENGTH_TRESH = settings.LENGTH_TRESH_MODE_JOINCUT
DISTANCE_TRESH_CHECK_SIFT = settings.CLUSTER_DISTANCE_TRESHOLD_MODE_JOINCUT_CHECK_SIFT
results = []
was_joined_by_dist = False
if 'dist' in check_mode:
if dist < DIST_TRESH:
results.append(True)
was_joined_by_dist = True
else:
results.append(False)
if 'sift' in check_mode and img1 and img2:
if not was_joined_by_dist:
dist = img1.get_distance(img2,from_object=True)
if dist > DISTANCE_TRESH_CHECK_SIFT:
img1 = prepare_img_for_sift(img1)
img2 = prepare_img_for_sift(img2)
loc_desc1 = (img1.loc, img1.desc)
loc_desc2 = (img2.loc, img2.desc)
im1, im2, mscores,qom,mpercent = get_kpm(loc_desc1, loc_desc2, mode='only_match')
if qom > settings.QOM_MINIMUM_SCENEJOIN:
results.append(True)
else:
results.append(False)
if 'length' in check_mode:
length_time = frame_diff_to_milisecs(length_diff,fps)
if length_time <= float(LENGTH_TRESH)*1000.0:
results.append(True)
else:
results.append(False)
if 'time_diff' in check_mode:
time_diff = frame_diff_to_milisecs(diff,fps)
if time_diff<(float(TIMEDIFF_TRESH)*1000.0):
results.append(True)
else:
results.append(False)
if 'AND' in check_mode:
if False in results: return False
else: return True
if 'OR' in check_mode:
if True in results: return True
else: return False
else:
return False