Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / python / google-api-python-client / 715bd7f9ca9a324a05ee05a6476af383e54930f9 / . / docs / dyn / videointelligence_v1.videos.html
blob: 914734528edaaa6956cb4e49bd8455108e01f01a [file] [log] [blame]
Bu Sun Kim715bd7f2019-06-14 16:50:42 -0700[diff] [blame^]1<html><body>
2<style>
3
4body, h1, h2, h3, div, span, p, pre, a {
5 margin: 0;
6 padding: 0;
7 border: 0;
8 font-weight: inherit;
9 font-style: inherit;
10 font-size: 100%;
11 font-family: inherit;
12 vertical-align: baseline;
13}
14
15body {
16 font-size: 13px;
17 padding: 1em;
18}
19
20h1 {
21 font-size: 26px;
22 margin-bottom: 1em;
23}
24
25h2 {
26 font-size: 24px;
27 margin-bottom: 1em;
28}
29
30h3 {
31 font-size: 20px;
32 margin-bottom: 1em;
33 margin-top: 1em;
34}
35
36pre, code {
37 line-height: 1.5;
38 font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
39}
40
41pre {
42 margin-top: 0.5em;
43}
44
45h1, h2, h3, p {
46 font-family: Arial, sans serif;
47}
48
49h1, h2, h3 {
50 border-bottom: solid #CCC 1px;
51}
52
53.toc_element {
54 margin-top: 0.5em;
55}
56
57.firstline {
58 margin-left: 2 em;
59}
60
61.method {
62 margin-top: 1em;
63 border: solid 1px #CCC;
64 padding: 1em;
65 background: #EEE;
66}
67
68.details {
69 font-weight: bold;
70 font-size: 14px;
71}
72
73</style>
74
75<h1><a href="videointelligence_v1.html">Cloud Video Intelligence API</a> . <a href="videointelligence_v1.videos.html">videos</a></h1>
76<h2>Instance Methods</h2>
77<p class="toc_element">
78 <code><a href="#annotate">annotate(body, x__xgafv=None)</a></code></p>
79<p class="firstline">Performs asynchronous video annotation. Progress and results can be</p>
80<h3>Method Details</h3>
81<div class="method">
82 <code class="details" id="annotate">annotate(body, x__xgafv=None)</code>
83 <pre>Performs asynchronous video annotation. Progress and results can be
84retrieved through the `google.longrunning.Operations` interface.
85`Operation.metadata` contains `AnnotateVideoProgress` (progress).
86`Operation.response` contains `AnnotateVideoResponse` (results).
87
88Args:
89 body: object, The request body. (required)
90 The object takes the form of:
91
92{ # Video annotation request.
93 "videoContext": { # Video context and/or feature-specific parameters. # Additional video context and/or feature-specific parameters.
94 "shotChangeDetectionConfig": { # Config for SHOT_CHANGE_DETECTION. # Config for SHOT_CHANGE_DETECTION.
95 "model": "A String", # Model to use for shot change detection.
96 # Supported values: "builtin/stable" (the default if unset) and
97 # "builtin/latest".
98 },
99 "textDetectionConfig": { # Config for TEXT_DETECTION. # Config for TEXT_DETECTION.
100 "languageHints": [ # Language hint can be specified if the language to be detected is known a
101 # priori. It can increase the accuracy of the detection. Language hint must
102 # be language code in BCP-47 format.
103 #
104 # Automatic language detection is performed if no hint is provided.
105 "A String",
106 ],
107 "model": "A String", # Model to use for text detection.
108 # Supported values: "builtin/stable" (the default if unset) and
109 # "builtin/latest".
110 },
111 "speechTranscriptionConfig": { # Config for SPEECH_TRANSCRIPTION. # Config for SPEECH_TRANSCRIPTION.
112 "languageCode": "A String", # *Required* The language of the supplied audio as a
113 # [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
114 # Example: "en-US".
115 # See [Language Support](https://cloud.google.com/speech/docs/languages)
116 # for a list of the currently supported language codes.
117 "filterProfanity": True or False, # *Optional* If set to `true`, the server will attempt to filter out
118 # profanities, replacing all but the initial character in each filtered word
119 # with asterisks, e.g. "f***". If set to `false` or omitted, profanities
120 # won't be filtered out.
121 "enableAutomaticPunctuation": True or False, # *Optional* If 'true', adds punctuation to recognition result hypotheses.
122 # This feature is only available in select languages. Setting this for
123 # requests in other languages has no effect at all. The default 'false' value
124 # does not add punctuation to result hypotheses. NOTE: "This is currently
125 # offered as an experimental service, complimentary to all users. In the
126 # future this may be exclusively available as a premium feature."
127 "enableSpeakerDiarization": True or False, # *Optional* If 'true', enables speaker detection for each recognized word in
128 # the top alternative of the recognition result using a speaker_tag provided
129 # in the WordInfo.
130 # Note: When this is true, we send all the words from the beginning of the
131 # audio for the top alternative in every consecutive responses.
132 # This is done in order to improve our speaker tags as our models learn to
133 # identify the speakers in the conversation over time.
134 "maxAlternatives": 42, # *Optional* Maximum number of recognition hypotheses to be returned.
135 # Specifically, the maximum number of `SpeechRecognitionAlternative` messages
136 # within each `SpeechTranscription`. The server may return fewer than
137 # `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will
138 # return a maximum of one. If omitted, will return a maximum of one.
139 "audioTracks": [ # *Optional* For file formats, such as MXF or MKV, supporting multiple audio
140 # tracks, specify up to two tracks. Default: track 0.
141 42,
142 ],
143 "diarizationSpeakerCount": 42, # *Optional*
144 # If set, specifies the estimated number of speakers in the conversation.
145 # If not set, defaults to '2'.
146 # Ignored unless enable_speaker_diarization is set to true.
147 "enableWordConfidence": True or False, # *Optional* If `true`, the top result includes a list of words and the
148 # confidence for those words. If `false`, no word-level confidence
149 # information is returned. The default is `false`.
150 "speechContexts": [ # *Optional* A means to provide context to assist the speech recognition.
151 { # Provides "hints" to the speech recognizer to favor specific words and phrases
152 # in the results.
153 "phrases": [ # *Optional* A list of strings containing words and phrases "hints" so that
154 # the speech recognition is more likely to recognize them. This can be used
155 # to improve the accuracy for specific words and phrases, for example, if
156 # specific commands are typically spoken by the user. This can also be used
157 # to add additional words to the vocabulary of the recognizer. See
158 # [usage limits](https://cloud.google.com/speech/limits#content).
159 "A String",
160 ],
161 },
162 ],
163 },
164 "segments": [ # Video segments to annotate. The segments may overlap and are not required
165 # to be contiguous or span the whole video. If unspecified, each video is
166 # treated as a single segment.
167 { # Video segment.
168 "endTimeOffset": "A String", # Time-offset, relative to the beginning of the video,
169 # corresponding to the end of the segment (inclusive).
170 "startTimeOffset": "A String", # Time-offset, relative to the beginning of the video,
171 # corresponding to the start of the segment (inclusive).
172 },
173 ],
174 "labelDetectionConfig": { # Config for LABEL_DETECTION. # Config for LABEL_DETECTION.
175 "labelDetectionMode": "A String", # What labels should be detected with LABEL_DETECTION, in addition to
176 # video-level labels or segment-level labels.
177 # If unspecified, defaults to `SHOT_MODE`.
178 "model": "A String", # Model to use for label detection.
179 # Supported values: "builtin/stable" (the default if unset) and
180 # "builtin/latest".
181 "stationaryCamera": True or False, # Whether the video has been shot from a stationary (i.e. non-moving) camera.
182 # When set to true, might improve detection accuracy for moving objects.
183 # Should be used with `SHOT_AND_FRAME_MODE` enabled.
184 "frameConfidenceThreshold": 3.14, # The confidence threshold we perform filtering on the labels from
185 # frame-level detection. If not set, it is set to 0.4 by default. The valid
186 # range for this threshold is [0.1, 0.9]. Any value set outside of this
187 # range will be clipped.
188 # Note: for best results please follow the default threshold. We will update
189 # the default threshold everytime when we release a new model.
190 "videoConfidenceThreshold": 3.14, # The confidence threshold we perform filtering on the labels from
191 # video-level and shot-level detections. If not set, it is set to 0.3 by
192 # default. The valid range for this threshold is [0.1, 0.9]. Any value set
193 # outside of this range will be clipped.
194 # Note: for best results please follow the default threshold. We will update
195 # the default threshold everytime when we release a new model.
196 },
197 "explicitContentDetectionConfig": { # Config for EXPLICIT_CONTENT_DETECTION. # Config for EXPLICIT_CONTENT_DETECTION.
198 "model": "A String", # Model to use for explicit content detection.
199 # Supported values: "builtin/stable" (the default if unset) and
200 # "builtin/latest".
201 },
202 "objectTrackingConfig": { # Config for OBJECT_TRACKING. # Config for OBJECT_TRACKING.
203 "model": "A String", # Model to use for object tracking.
204 # Supported values: "builtin/stable" (the default if unset) and
205 # "builtin/latest".
206 },
207 },
208 "features": [ # Requested video annotation features.
209 "A String",
210 ],
211 "inputContent": "A String", # The video data bytes.
212 # If unset, the input video(s) should be specified via `input_uri`.
213 # If set, `input_uri` should be unset.
214 "inputUri": "A String", # Input video location. Currently, only
215 # [Google Cloud Storage](https://cloud.google.com/storage/) URIs are
216 # supported, which must be specified in the following format:
217 # `gs://bucket-id/object-id` (other URI formats return
218 # google.rpc.Code.INVALID_ARGUMENT). For more information, see
219 # [Request URIs](/storage/docs/reference-uris).
220 # A video URI may include wildcards in `object-id`, and thus identify
221 # multiple videos. Supported wildcards: '*' to match 0 or more characters;
222 # '?' to match 1 character. If unset, the input video should be embedded
223 # in the request as `input_content`. If set, `input_content` should be unset.
224 "locationId": "A String", # Optional cloud region where annotation should take place. Supported cloud
225 # regions: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region
226 # is specified, a region will be determined based on video file location.
227 "outputUri": "A String", # Optional location where the output (in JSON format) should be stored.
228 # Currently, only [Google Cloud Storage](https://cloud.google.com/storage/)
229 # URIs are supported, which must be specified in the following format:
230 # `gs://bucket-id/object-id` (other URI formats return
231 # google.rpc.Code.INVALID_ARGUMENT). For more information, see
232 # [Request URIs](/storage/docs/reference-uris).
233 }
234
235 x__xgafv: string, V1 error format.
236 Allowed values
237 1 - v1 error format
238 2 - v2 error format
239
240Returns:
241 An object of the form:
242
243 { # This resource represents a long-running operation that is the result of a
244 # network API call.
245 "metadata": { # Service-specific metadata associated with the operation. It typically
246 # contains progress information and common metadata such as create time.
247 # Some services might not provide such metadata. Any method that returns a
248 # long-running operation should document the metadata type, if any.
249 "a_key": "", # Properties of the object. Contains field @type with type URL.
250 },
251 "error": { # The `Status` type defines a logical error model that is suitable for # The error result of the operation in case of failure or cancellation.
252 # different programming environments, including REST APIs and RPC APIs. It is
253 # used by [gRPC](https://github.com/grpc). Each `Status` message contains
254 # three pieces of data: error code, error message, and error details.
255 #
256 # You can find out more about this error model and how to work with it in the
257 # [API Design Guide](https://cloud.google.com/apis/design/errors).
258 "message": "A String", # A developer-facing error message, which should be in English. Any
259 # user-facing error message should be localized and sent in the
260 # google.rpc.Status.details field, or localized by the client.
261 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
262 "details": [ # A list of messages that carry the error details. There is a common set of
263 # message types for APIs to use.
264 {
265 "a_key": "", # Properties of the object. Contains field @type with type URL.
266 },
267 ],
268 },
269 "done": True or False, # If the value is `false`, it means the operation is still in progress.
270 # If `true`, the operation is completed, and either `error` or `response` is
271 # available.
272 "response": { # The normal response of the operation in case of success. If the original
273 # method returns no data on success, such as `Delete`, the response is
274 # `google.protobuf.Empty`. If the original method is standard
275 # `Get`/`Create`/`Update`, the response should be the resource. For other
276 # methods, the response should have the type `XxxResponse`, where `Xxx`
277 # is the original method name. For example, if the original method name
278 # is `TakeSnapshot()`, the inferred response type is
279 # `TakeSnapshotResponse`.
280 "a_key": "", # Properties of the object. Contains field @type with type URL.
281 },
282 "name": "A String", # The server-assigned name, which is only unique within the same service that
283 # originally returns it. If you use the default HTTP mapping, the
284 # `name` should be a resource name ending with `operations/{unique_id}`.
285 }</pre>
286</div>
287
288</body></html>