This repository was archived by the owner on Nov 29, 2023. It is now read-only.
Repository navigation
Expand file tree
/
Copy pathanalyze.py
More file actions
589 lines (487 loc) · 22.5 KB
/
Copy pathanalyze.py
File metadata and controls
589 lines (487 loc) · 22.5 KB
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
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
#!/usr/bin/env python
# Copyright 2017 Google LLC. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""This application demonstrates label detection,
explicit content, and shot change detection using the Google Cloud API.
Usage Examples:
python analyze.py labels gs://cloud-samples-data/video/chicago.mp4
python analyze.py labels_file resources/cat.mp4
python analyze.py shots gs://cloud-samples-data/video/gbikes_dinosaur.mp4
python analyze.py explicit_content \
gs://cloud-samples-data/video/gbikes_dinosaur.mp4
python analyze.py text_gcs \
gs://cloud-samples-data/video/googlework_tiny.mp4
python analyze.py text_file resources/googlework_tiny.mp4
python analyze.py objects_gcs gs://cloud-samples-data/video/cat.mp4
python analyze.py objects_file resources/cat.mp4
"""
import argparse
import io
from google.cloud import videointelligence
def analyze_explicit_content(path):
# [START video_analyze_explicit_content]
""" Detects explicit content from the GCS path to a video. """
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.EXPLICIT_CONTENT_DETECTION]
operation = video_client.annotate_video(
request={"features": features, "input_uri": path}
)
print("\nProcessing video for explicit content annotations:")
result = operation.result(timeout=90)
print("\nFinished processing.")
# Retrieve first result because a single video was processed
for frame in result.annotation_results[0].explicit_annotation.frames:
likelihood = videointelligence.Likelihood(frame.pornography_likelihood)
frame_time = frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
print("Time: {}s".format(frame_time))
print("\tpornography: {}".format(likelihood.name))
# [END video_analyze_explicit_content]
def analyze_labels(path):
# [START video_analyze_labels_gcs]
""" Detects labels given a GCS path. """
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.LABEL_DETECTION]
mode = videointelligence.LabelDetectionMode.SHOT_AND_FRAME_MODE
config = videointelligence.LabelDetectionConfig(label_detection_mode=mode)
context = videointelligence.VideoContext(label_detection_config=config)
operation = video_client.annotate_video(
request={"features": features, "input_uri": path, "video_context": context}
)
print("\nProcessing video for label annotations:")
result = operation.result(timeout=180)
print("\nFinished processing.")
# Process video/segment level label annotations
segment_labels = result.annotation_results[0].segment_label_annotations
for i, segment_label in enumerate(segment_labels):
print("Video label description: {}".format(segment_label.entity.description))
for category_entity in segment_label.category_entities:
print(
"\tLabel category description: {}".format(category_entity.description)
)
for i, segment in enumerate(segment_label.segments):
start_time = (
segment.segment.start_time_offset.seconds
+ segment.segment.start_time_offset.microseconds / 1e6
)
end_time = (
segment.segment.end_time_offset.seconds
+ segment.segment.end_time_offset.microseconds / 1e6
)
positions = "{}s to {}s".format(start_time, end_time)
confidence = segment.confidence
print("\tSegment {}: {}".format(i, positions))
print("\tConfidence: {}".format(confidence))
print("\n")
# Process shot level label annotations
shot_labels = result.annotation_results[0].shot_label_annotations
for i, shot_label in enumerate(shot_labels):
print("Shot label description: {}".format(shot_label.entity.description))
for category_entity in shot_label.category_entities:
print(
"\tLabel category description: {}".format(category_entity.description)
)
for i, shot in enumerate(shot_label.segments):
start_time = (
shot.segment.start_time_offset.seconds
+ shot.segment.start_time_offset.microseconds / 1e6
)
end_time = (
shot.segment.end_time_offset.seconds
+ shot.segment.end_time_offset.microseconds / 1e6
)
positions = "{}s to {}s".format(start_time, end_time)
confidence = shot.confidence
print("\tSegment {}: {}".format(i, positions))
print("\tConfidence: {}".format(confidence))
print("\n")
# Process frame level label annotations
frame_labels = result.annotation_results[0].frame_label_annotations
for i, frame_label in enumerate(frame_labels):
print("Frame label description: {}".format(frame_label.entity.description))
for category_entity in frame_label.category_entities:
print(
"\tLabel category description: {}".format(category_entity.description)
)
# Each frame_label_annotation has many frames,
# here we print information only about the first frame.
frame = frame_label.frames[0]
time_offset = frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
print("\tFirst frame time offset: {}s".format(time_offset))
print("\tFirst frame confidence: {}".format(frame.confidence))
print("\n")
# [END video_analyze_labels_gcs]
def analyze_labels_file(path):
# [START video_analyze_labels]
"""Detect labels given a file path."""
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.LABEL_DETECTION]
with io.open(path, "rb") as movie:
input_content = movie.read()
operation = video_client.annotate_video(
request={"features": features, "input_content": input_content}
)
print("\nProcessing video for label annotations:")
result = operation.result(timeout=90)
print("\nFinished processing.")
# Process video/segment level label annotations
segment_labels = result.annotation_results[0].segment_label_annotations
for i, segment_label in enumerate(segment_labels):
print("Video label description: {}".format(segment_label.entity.description))
for category_entity in segment_label.category_entities:
print(
"\tLabel category description: {}".format(category_entity.description)
)
for i, segment in enumerate(segment_label.segments):
start_time = (
segment.segment.start_time_offset.seconds
+ segment.segment.start_time_offset.microseconds / 1e6
)
end_time = (
segment.segment.end_time_offset.seconds
+ segment.segment.end_time_offset.microseconds / 1e6
)
positions = "{}s to {}s".format(start_time, end_time)
confidence = segment.confidence
print("\tSegment {}: {}".format(i, positions))
print("\tConfidence: {}".format(confidence))
print("\n")
# Process shot level label annotations
shot_labels = result.annotation_results[0].shot_label_annotations
for i, shot_label in enumerate(shot_labels):
print("Shot label description: {}".format(shot_label.entity.description))
for category_entity in shot_label.category_entities:
print(
"\tLabel category description: {}".format(category_entity.description)
)
for i, shot in enumerate(shot_label.segments):
start_time = (
shot.segment.start_time_offset.seconds
+ shot.segment.start_time_offset.microseconds / 1e6
)
end_time = (
shot.segment.end_time_offset.seconds
+ shot.segment.end_time_offset.microseconds / 1e6
)
positions = "{}s to {}s".format(start_time, end_time)
confidence = shot.confidence
print("\tSegment {}: {}".format(i, positions))
print("\tConfidence: {}".format(confidence))
print("\n")
# Process frame level label annotations
frame_labels = result.annotation_results[0].frame_label_annotations
for i, frame_label in enumerate(frame_labels):
print("Frame label description: {}".format(frame_label.entity.description))
for category_entity in frame_label.category_entities:
print(
"\tLabel category description: {}".format(category_entity.description)
)
# Each frame_label_annotation has many frames,
# here we print information only about the first frame.
frame = frame_label.frames[0]
time_offset = frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
print("\tFirst frame time offset: {}s".format(time_offset))
print("\tFirst frame confidence: {}".format(frame.confidence))
print("\n")
# [END video_analyze_labels]
def analyze_shots(path):
# [START video_analyze_shots]
""" Detects camera shot changes. """
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.SHOT_CHANGE_DETECTION]
operation = video_client.annotate_video(
request={"features": features, "input_uri": path}
)
print("\nProcessing video for shot change annotations:")
result = operation.result(timeout=90)
print("\nFinished processing.")
# first result is retrieved because a single video was processed
for i, shot in enumerate(result.annotation_results[0].shot_annotations):
start_time = (
shot.start_time_offset.seconds + shot.start_time_offset.microseconds / 1e6
)
end_time = (
shot.end_time_offset.seconds + shot.end_time_offset.microseconds / 1e6
)
print("\tShot {}: {} to {}".format(i, start_time, end_time))
# [END video_analyze_shots]
def speech_transcription(path):
# [START video_speech_transcription_gcs]
"""Transcribe speech from a video stored on GCS."""
from google.cloud import videointelligence
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.SPEECH_TRANSCRIPTION]
config = videointelligence.SpeechTranscriptionConfig(
language_code="en-US", enable_automatic_punctuation=True
)
video_context = videointelligence.VideoContext(speech_transcription_config=config)
operation = video_client.annotate_video(
request={
"features": features,
"input_uri": path,
"video_context": video_context,
}
)
print("\nProcessing video for speech transcription.")
result = operation.result(timeout=600)
# There is only one annotation_result since only
# one video is processed.
annotation_results = result.annotation_results[0]
for speech_transcription in annotation_results.speech_transcriptions:
# The number of alternatives for each transcription is limited by
# SpeechTranscriptionConfig.max_alternatives.
# Each alternative is a different possible transcription
# and has its own confidence score.
for alternative in speech_transcription.alternatives:
print("Alternative level information:")
print("Transcript: {}".format(alternative.transcript))
print("Confidence: {}\n".format(alternative.confidence))
print("Word level information:")
for word_info in alternative.words:
word = word_info.word
start_time = word_info.start_time
end_time = word_info.end_time
print(
"\t{}s - {}s: {}".format(
start_time.seconds + start_time.microseconds * 1e-6,
end_time.seconds + end_time.microseconds * 1e-6,
word,
)
)
# [END video_speech_transcription_gcs]
def video_detect_text_gcs(input_uri):
# [START video_detect_text_gcs]
"""Detect text in a video stored on GCS."""
from google.cloud import videointelligence
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.TEXT_DETECTION]
operation = video_client.annotate_video(
request={"features": features, "input_uri": input_uri}
)
print("\nProcessing video for text detection.")
result = operation.result(timeout=600)
# The first result is retrieved because a single video was processed.
annotation_result = result.annotation_results[0]
for text_annotation in annotation_result.text_annotations:
print("\nText: {}".format(text_annotation.text))
# Get the first text segment
text_segment = text_annotation.segments[0]
start_time = text_segment.segment.start_time_offset
end_time = text_segment.segment.end_time_offset
print(
"start_time: {}, end_time: {}".format(
start_time.seconds + start_time.microseconds * 1e-6,
end_time.seconds + end_time.microseconds * 1e-6,
)
)
print("Confidence: {}".format(text_segment.confidence))
# Show the result for the first frame in this segment.
frame = text_segment.frames[0]
time_offset = frame.time_offset
print(
"Time offset for the first frame: {}".format(
time_offset.seconds + time_offset.microseconds * 1e-6
)
)
print("Rotated Bounding Box Vertices:")
for vertex in frame.rotated_bounding_box.vertices:
print("\tVertex.x: {}, Vertex.y: {}".format(vertex.x, vertex.y))
# [END video_detect_text_gcs]
def video_detect_text(path):
# [START video_detect_text]
"""Detect text in a local video."""
from google.cloud import videointelligence
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.TEXT_DETECTION]
video_context = videointelligence.VideoContext()
with io.open(path, "rb") as file:
input_content = file.read()
operation = video_client.annotate_video(
request={
"features": features,
"input_content": input_content,
"video_context": video_context,
}
)
print("\nProcessing video for text detection.")
result = operation.result(timeout=300)
# The first result is retrieved because a single video was processed.
annotation_result = result.annotation_results[0]
for text_annotation in annotation_result.text_annotations:
print("\nText: {}".format(text_annotation.text))
# Get the first text segment
text_segment = text_annotation.segments[0]
start_time = text_segment.segment.start_time_offset
end_time = text_segment.segment.end_time_offset
print(
"start_time: {}, end_time: {}".format(
start_time.seconds + start_time.microseconds * 1e-6,
end_time.seconds + end_time.microseconds * 1e-6,
)
)
print("Confidence: {}".format(text_segment.confidence))
# Show the result for the first frame in this segment.
frame = text_segment.frames[0]
time_offset = frame.time_offset
print(
"Time offset for the first frame: {}".format(
time_offset.seconds + time_offset.microseconds * 1e-6
)
)
print("Rotated Bounding Box Vertices:")
for vertex in frame.rotated_bounding_box.vertices:
print("\tVertex.x: {}, Vertex.y: {}".format(vertex.x, vertex.y))
# [END video_detect_text]
def track_objects_gcs(gcs_uri):
# [START video_object_tracking_gcs]
"""Object tracking in a video stored on GCS."""
from google.cloud import videointelligence
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.OBJECT_TRACKING]
operation = video_client.annotate_video(
request={"features": features, "input_uri": gcs_uri}
)
print("\nProcessing video for object annotations.")
result = operation.result(timeout=300)
print("\nFinished processing.\n")
# The first result is retrieved because a single video was processed.
object_annotations = result.annotation_results[0].object_annotations
for object_annotation in object_annotations:
print("Entity description: {}".format(object_annotation.entity.description))
if object_annotation.entity.entity_id:
print("Entity id: {}".format(object_annotation.entity.entity_id))
print(
"Segment: {}s to {}s".format(
object_annotation.segment.start_time_offset.seconds
+ object_annotation.segment.start_time_offset.microseconds / 1e6,
object_annotation.segment.end_time_offset.seconds
+ object_annotation.segment.end_time_offset.microseconds / 1e6,
)
)
print("Confidence: {}".format(object_annotation.confidence))
# Here we print only the bounding box of the first frame in the segment
frame = object_annotation.frames[0]
box = frame.normalized_bounding_box
print(
"Time offset of the first frame: {}s".format(
frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
)
)
print("Bounding box position:")
print("\tleft : {}".format(box.left))
print("\ttop : {}".format(box.top))
print("\tright : {}".format(box.right))
print("\tbottom: {}".format(box.bottom))
print("\n")
# [END video_object_tracking_gcs]
def track_objects(path):
# [START video_object_tracking]
"""Object tracking in a local video."""
from google.cloud import videointelligence
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.Feature.OBJECT_TRACKING]
with io.open(path, "rb") as file:
input_content = file.read()
operation = video_client.annotate_video(
request={"features": features, "input_content": input_content}
)
print("\nProcessing video for object annotations.")
result = operation.result(timeout=300)
print("\nFinished processing.\n")
# The first result is retrieved because a single video was processed.
object_annotations = result.annotation_results[0].object_annotations
# Get only the first annotation for demo purposes.
object_annotation = object_annotations[0]
print("Entity description: {}".format(object_annotation.entity.description))
if object_annotation.entity.entity_id:
print("Entity id: {}".format(object_annotation.entity.entity_id))
print(
"Segment: {}s to {}s".format(
object_annotation.segment.start_time_offset.seconds
+ object_annotation.segment.start_time_offset.microseconds / 1e6,
object_annotation.segment.end_time_offset.seconds
+ object_annotation.segment.end_time_offset.microseconds / 1e6,
)
)
print("Confidence: {}".format(object_annotation.confidence))
# Here we print only the bounding box of the first frame in this segment
frame = object_annotation.frames[0]
box = frame.normalized_bounding_box
print(
"Time offset of the first frame: {}s".format(
frame.time_offset.seconds + frame.time_offset.microseconds / 1e6
)
)
print("Bounding box position:")
print("\tleft : {}".format(box.left))
print("\ttop : {}".format(box.top))
print("\tright : {}".format(box.right))
print("\tbottom: {}".format(box.bottom))
print("\n")
# [END video_object_tracking]
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
)
subparsers = parser.add_subparsers(dest="command")
analyze_labels_parser = subparsers.add_parser("labels", help=analyze_labels.__doc__)
analyze_labels_parser.add_argument("path")
analyze_labels_file_parser = subparsers.add_parser(
"labels_file", help=analyze_labels_file.__doc__
)
analyze_labels_file_parser.add_argument("path")
analyze_explicit_content_parser = subparsers.add_parser(
"explicit_content", help=analyze_explicit_content.__doc__
)
analyze_explicit_content_parser.add_argument("path")
analyze_shots_parser = subparsers.add_parser("shots", help=analyze_shots.__doc__)
analyze_shots_parser.add_argument("path")
transcribe_speech_parser = subparsers.add_parser(
"transcribe", help=speech_transcription.__doc__
)
transcribe_speech_parser.add_argument("path")
detect_text_parser = subparsers.add_parser(
"text_gcs", help=video_detect_text_gcs.__doc__
)
detect_text_parser.add_argument("path")
detect_text_file_parser = subparsers.add_parser(
"text_file", help=video_detect_text.__doc__
)
detect_text_file_parser.add_argument("path")
tack_objects_parser = subparsers.add_parser(
"objects_gcs", help=track_objects_gcs.__doc__
)
tack_objects_parser.add_argument("path")
tack_objects_file_parser = subparsers.add_parser(
"objects_file", help=track_objects.__doc__
)
tack_objects_file_parser.add_argument("path")
args = parser.parse_args()
if args.command == "labels":
analyze_labels(args.path)
if args.command == "labels_file":
analyze_labels_file(args.path)
if args.command == "shots":
analyze_shots(args.path)
if args.command == "explicit_content":
analyze_explicit_content(args.path)
if args.command == "transcribe":
speech_transcription(args.path)
if args.command == "text_gcs":
video_detect_text_gcs(args.path)
if args.command == "text_file":
video_detect_text(args.path)
if args.command == "objects_gcs":
track_objects_gcs(args.path)
if args.command == "objects_file":
track_objects(args.path)