def __generate_distance_matrix_on_separate_features(video1, video2):
v1_shot_numbers = SimilarityCalculator.__get_video_shots(video1)
v2_shot_numbers = SimilarityCalculator.__get_video_shots(video2)
matrix = []
for v1_shot_number in v1_shot_numbers:
row = []
for v2_shot_number in v2_shot_numbers:
v1_shot = video1.shots[str(v1_shot_number)]
v2_shot = video2.shots[str(v2_shot_number)]
distance = 0
if v1_shot.cluster != v2_shot.cluster:
v1_audio_features = SimilarityCalculator.__get_audio_features(
v1_shot.features)
v1_video_features = SimilarityCalculator.__get_audio_features(
v1_shot.features)
v2_audio_features = SimilarityCalculator.__get_audio_features(
v2_shot.features)
v2_video_features = SimilarityCalculator.__get_audio_features(
v2_shot.features)
audio_distance = utl.calculate_distance(
v1_audio_features, v2_audio_features)
video_distance = utl.calculate_distance(
v1_video_features, v2_video_features)
distance = 0.5 * (audio_distance + video_distance)
row.append(distance)
matrix.append(row)
return matrix
def generate_average_distance_csv(features_csv, distance_output):
feature_vectors = get_features_list(features_csv)
feature_vector_count = len(feature_vectors)
print "generating distance csv..."
distance_count = 0
distance_sum = 0
iteration = 1
for i in range(feature_vector_count):
if i + 1 > feature_vector_count:
break
for j in range(i + 1, feature_vector_count):
v1 = feature_vectors[i]
v2 = feature_vectors[j]
distance_sum += utility.calculate_distance(v1, v2)
distance_count += 1
utility.print_progress_bar(iteration, feature_vector_count)
iteration += 1
with open(distance_output, 'wb') as f:
the_writer = csv.writer(f)
headers = ["file", "average_distance"]
the_writer.writerow(headers)
vector = [features_csv, float(distance_sum) / float(distance_count)]
the_writer.writerow(vector)
f.close()
def get_two_categories_distance(category_all_feature_vectors,
category_center_feature_vector):
category_distance_list = []
for category_feature_vector in category_all_feature_vectors:
distance = utl.calculate_distance(category_feature_vector,
category_center_feature_vector)
category_distance_list.append(distance)
return mean(category_distance_list)
def __generate_full_distance_matrix(video1, video2):
v1_shot_numbers = SimilarityCalculator.__get_video_shots(video1)
v2_shots_numbers = SimilarityCalculator.__get_video_shots(video2)
row_count = len(v1_shot_numbers)
column_count = len(v2_shots_numbers)
matrix = []
for v1_shot_number in v1_shot_numbers:
row = []
for v2_shot_number in v2_shots_numbers:
v1_shot = video1.shots[str(v1_shot_number)]
v2_shot = video2.shots[str(v2_shot_number)]
distance = utl.calculate_distance(v1_shot.features,
v2_shot.features)
row.append(distance)
matrix.append(row)
return matrix, row_count, column_count
def calculate_distance_mean(category, category_data_set):
print("calculating distance mean for '" + category + "' category ...")
category_data_set_len = len(category_data_set) # type: int
distance_list = []
for i in range(0, category_data_set_len):
for j in range(i + 1, category_data_set_len):
vec1 = category_data_set[i]
vec2 = category_data_set[j]
distance_list.append(utl.calculate_distance(vec1, vec2))
utl.print_progress_bar(i + 1, category_data_set_len)
print("")
print("distance mean calculation for category '" + category +
"' has been completed!")
return calculate_mean(distance_list)
def get_category_self_distance_dictionary(category_all_features,
category_center_features):
category_distance_dictionary = {}
for category_name_average, category_average_feature_vector in category_center_features.iteritems(
):
category_distance_dictionary[category_name_average] = []
for category_complete_feature_vector in category_all_features[
category_name_average]:
distance = utl.calculate_distance(
category_average_feature_vector,
category_complete_feature_vector)
category_distance_dictionary[category_name_average].append(
distance)
category_average_distance_dictionary = {}
for category, distance_list in category_distance_dictionary.iteritems():
category_average_distance_dictionary[category] = mean(distance_list)
return category_average_distance_dictionary