OLD | NEW |
---|---|
(Empty) | |
1 // Copyright 2017 The Chromium Authors. All rights reserved. | |
2 // Use of this source code is governed by a BSD-style license that can be | |
3 // found in the LICENSE file. | |
4 | |
5 // Private API for communicating with and receiving real-time media perception | |
6 // information from an computer vision + machine intelligence binary. | |
7 [platforms=("chromeos"), | |
8 implemented_in = "extensions/browser/api/media_perception_private/media_percept ion_private_api.h"] | |
tbarzic
2017/05/05 21:10:41
I don't think you need this - this seems to be the
Luke Sorenson
2017/05/08 19:06:07
Done. In https://codereview.chromium.org/286020300
| |
9 | |
10 namespace mediaPerceptionPrivate { | |
11 enum Status { | |
12 // An error occurred that needs to be propagated to the frontend. | |
tbarzic
2017/05/05 21:10:41
I'd drop the "that needs to be propagated to the f
Luke Sorenson
2017/05/08 19:06:07
Done. In https://codereview.chromium.org/28602030
| |
13 ERROR, | |
14 | |
15 // Unable to reach media analysis process. | |
16 TIMEOUT, | |
17 | |
18 // Media analytics process waiting to be started. | |
19 UNINITIALIZED, | |
20 | |
21 // Analysis process running but not recieving frames. | |
tbarzic
2017/05/05 21:10:41
Can you explain the difference between STARTED/RUN
Luke Sorenson
2017/05/08 19:06:07
Done. In https://codereview.chromium.org/286020300
| |
22 STARTED, | |
23 | |
24 // Analysis process running and injesting frames. | |
25 RUNNING, | |
26 | |
27 // Analysis process ready to be set to state RUNNING. | |
28 SUSPENDED | |
29 }; | |
30 | |
31 // The system and configuration state of the analysis process and v4lplugin. | |
32 dictionary State { | |
33 Status? status; | |
34 // Optionally add device context to setState command for starting | |
35 // media analytics process, so that the media analytics process can | |
36 // better select the right video device to open. | |
37 DOMString? deviceContext; | |
tbarzic
2017/05/05 21:10:41
Is this allowed only with setState(RUNNING)?
I.e.
Luke Sorenson
2017/05/08 19:06:07
Providing device context is only meaningful with s
| |
38 }; | |
39 | |
40 dictionary Point { | |
41 // x represents the horizontal distance from the top left corner of the | |
tbarzic
2017/05/05 21:10:41
drop "x represents" and "to the point"
Luke Sorenson
2017/05/08 19:06:07
Done.
| |
42 // image to the point. | |
43 double? x; | |
44 // y represents the vertical distance from the top left corner of the | |
tbarzic
2017/05/05 21:10:41
drop "y represents" and "to the point"
Luke Sorenson
2017/05/08 19:06:06
Done.
| |
45 // image to the point. | |
46 double? y; | |
tbarzic
2017/05/05 21:10:41
This seems like a required value - can you go thro
Luke Sorenson
2017/05/08 19:06:07
Because many of these Dictionary definitions are b
| |
47 }; | |
48 | |
49 dictionary BoundingBox { | |
50 // Specifies whether the points are normalized to the size of the image. | |
51 // If not set, the points are not normalized. | |
tbarzic
2017/05/05 21:10:41
"If not set, the points are not normalized" seems
Luke Sorenson
2017/05/08 19:06:07
Done :) In https://codereview.chromium.org/2860203
| |
52 boolean? normalized; | |
53 // The two points that define the corners of a bounding box. | |
54 Point? topLeft; | |
55 Point? bottomRight; | |
56 }; | |
57 | |
58 enum EntityType { | |
59 UNSPECIFIED, | |
60 FACE, | |
61 PERSON | |
62 }; | |
63 | |
64 dictionary Entity { | |
65 // A unique id associated with the detected entity, which can be used to | |
66 // track the entity over time. | |
67 long? id; | |
tbarzic
2017/05/05 21:10:41
why is this optional?
Luke Sorenson
2017/05/08 19:06:07
See above explanation about decision to use only o
tbarzic
2017/05/08 23:04:55
My idea was closer to dropping nonsensical message
| |
68 | |
69 EntityType? type; | |
70 | |
71 // Minimum box which captures entire detected entity. | |
72 BoundingBox? boundingBox; | |
73 | |
74 // A value for the quality of this detection. | |
75 double? confidence; | |
76 }; | |
77 | |
78 // The set of computer vision metadata for an image frame. | |
79 dictionary FramePerception { | |
80 long? frameId; | |
81 | |
82 long? frameWidthInPx; | |
83 long? frameHeightInPx; | |
84 // The timestamp associated with the frame (when its recieved by the | |
85 // analysis process). | |
86 double? timestamp; | |
87 | |
88 // The list of entities detected in this frame. | |
89 Entity[]? entities; | |
90 }; | |
91 | |
92 dictionary MediaPerception { | |
93 // The timestamp attached with when this data originated from the analysis | |
94 // process. | |
tbarzic
2017/05/05 21:10:41
I'd comment on relationship to timestamps in frame
Luke Sorenson
2017/05/08 19:06:07
Done.
| |
95 double? timestamp; | |
96 // An array of framePerceptions, often just one. | |
97 FramePerception[]? framePerceptions; | |
98 }; | |
99 | |
100 // TODO(lasoren): Change this interface based on the compressed images coming | |
101 // from the media analytics process. | |
102 dictionary ImageFrame { | |
103 long? width; | |
104 long? height; | |
105 // colorspace is defined in the same way as SimpleImage::ColorSpace. | |
tbarzic
2017/05/05 21:10:41
I'd avoid referencing SimpleImage::ColorSpace here
Luke Sorenson
2017/05/08 19:06:07
Acknowledged.
| |
106 long? colorspace; | |
107 // By default, 1 channel means Grayscale, 2 channels meangs Grayscale + Alph a, | |
tbarzic
2017/05/05 21:10:41
So this is the number of channels? maybe rename it
Luke Sorenson
2017/05/08 19:06:06
For now, since we not yet sure how we'll be repres
| |
108 // 3 channels means RGB, and 4 channels means RGBA. | |
109 long? channels; | |
110 // TODO(lasoren): Add compression format marker. | |
111 // The bytes of the image frame. | |
112 ArrayBuffer? frame; | |
113 }; | |
114 | |
115 dictionary PerceptionSample { | |
116 // The video analytics FramePerception for the associated image frame | |
117 // data. | |
118 FramePerception? framePerception; | |
119 // The image frame data for the associated FramePerception object. | |
120 ImageFrame? imageFrame; | |
121 }; | |
122 | |
123 dictionary Diagnostics { | |
124 // A buffer of image frames and the associated video analytics to be sent | |
125 // for diagnostics (when a user reports malfunction). | |
126 PerceptionSample[]? perceptionSamples; | |
127 }; | |
128 | |
129 callback StateCallback = void(State state); | |
130 | |
131 callback DiagnosticsCallback = void(Diagnostics diagnostics); | |
132 | |
133 interface Functions { | |
134 // Get the status of the media perception process. | |
135 // |callback| : The current State of the system. | |
136 static void getState(StateCallback callback); | |
137 | |
138 // Set the desired state of the system. | |
139 // |state| : A dictionary with the desired new state. | |
140 // |callback| : The State of the system after setting it. Verifies that | |
141 // the state was set as desired. | |
142 static void setState(State state, StateCallback callback); | |
143 | |
144 // Get a diagnostics buffer out of the video analytics process. | |
145 // |callback| : Returns a Diagnostics dictionary object which | |
146 // contains image frame data and associated detections to be logged. | |
147 static void getDiagnostics(DiagnosticsCallback callback); | |
148 }; | |
149 | |
150 interface Events { | |
151 // Fired when the analysis process has passed back to Chrome the current | |
152 // mediaPerception information. | |
153 // |mediaPerception| : The dictionary which contains a dump of everything | |
154 // the analysis process has detected or determined from the incoming media | |
155 // streams. | |
156 static void onMediaPerception(MediaPerception mediaPerception); | |
157 }; | |
158 }; | |
OLD | NEW |