Skip to content

Commit 1f9c0ba

Browse files
authored
Merge pull request #208071 from Juliako/featuredclothing
added featured clothing
2 parents 6634657 + 9fde49b commit 1f9c0ba

File tree

5 files changed

+105
-9
lines changed

5 files changed

+105
-9
lines changed
Lines changed: 84 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
1+
---
2+
title: People's featured clothing
3+
description: This article gives an overview of featured clothing images appearing in a video.
4+
ms.topic: conceptual
5+
ms.date: 11/15/2021
6+
ms.author: juliako
7+
---
8+
9+
# People's featured clothing (preview)
10+
11+
Azure Video Indexer enables you to get data on the featured clothing of an observed person. The people's featured clothing feature, helps to enable the following scenarios:
12+
13+
- Ads placement - using the featured clothing insight information, you can enable more targeted ads placement.
14+
- Video summarization - you can create a summary of the most interesting outfits appearing in the video.
15+
16+
## Viewing featured clothing
17+
18+
The featured clothing insight is available when indexing your file by choosing the Advanced option -> Advanced video or Advanced video + audio preset (under Video + audio indexing). Standard indexing will not include this insight.
19+
20+
:::image type="content" source="./media/detected-clothing/index-video.png" alt-text="This screenshot represents an indexing video option.":::
21+
22+
The featured clothing images are ranked based on some of the following factors: key moments of the video, general emotions from text or audio. The `id` property indicates the ranking index. For example, `"id": 1` signifies the most important featured clothing.
23+
24+
> [!NOTE]
25+
> The featured clothing currently can be viewed only from the artifact file.
26+
27+
1. In the right-upper corner, select to download the artifact zip file: **Download** -> **Artifact (ZIP)**
28+
1. Open `featuredclothing.zip`.
29+
30+
The .zip file contains two objects:
31+
32+
- `featuredclothing.map.json` - the file contains instances of each featured clothing, with the following properties:
33+
34+
- `id` – ranking index (`"id": 1` is the most important clothing).
35+
- `confidence` – the score of the featured clothing.
36+
- `frameIndex` – the best frame of the clothing.
37+
- `timestamp` – corresponding to the frameIndex.
38+
- `opBoundingBox` – bounding box of the person.
39+
- `faceBoundingBox` – bounding box of the person's face, if detected.
40+
- `fileName` – where the best frame of the clothing is saved.
41+
42+
An example of the featured clothing with `"id": 1`.
43+
44+
```
45+
"instances": [
46+
{
47+
"confidence": 0.98,
48+
"faceBoundingBox": {
49+
"x": 0.50158,
50+
"y": 0.10508,
51+
"width": 0.13589,
52+
"height": 0.45372
53+
},
54+
"fileName": "frame_12147.jpg",
55+
"frameIndex": 12147,
56+
"id": 1,
57+
"opBoundingBox": {
58+
"x": 0.34141,
59+
"y": 0.16667,
60+
"width": 0.28125,
61+
"height": 0.82083
62+
},
63+
"timestamp": "00:08:26.6311250"
64+
},
65+
```
66+
- `featuredclothing.frames.map` – this folder contains images of the best frames that the featured clothing appeared in, corresponding to the `fileName` property in each instance in `featuredclothing.map.json`.
67+
68+
## Limitations and assumptions
69+
70+
It's important to note the limitations of featured clothing to avoid or mitigate the effects of false detections of images with low quality or low relevancy. 
71+
72+
- Pre-condition for the featured clothing is that the person wearing the clothes can be found in the observed people insight.
73+
- If the face of a person wearing the featured clothing wasn't detected, the results won't include the faces bounding box.
74+
- If a person in a video wears more than one outfit, the algorithm selects its best outfit as a single featured clothing image.
75+
- When posed, the tracks are optimized to handle observed people who most often appear on the front.
76+
- Wrong detections may occur when people are overlapping.
77+
- Frames containing blurred people are more prone to low quality results.
78+
79+
For more information, see the [limitations of observed people](observed-people-tracing.md#limitations-and-assumptions).
80+
81+
## Next steps
82+
83+
- [Trace observed people in a video](observed-people-tracing.md)
84+
- [People's detected clothing](detected-clothing.md)

articles/azure-video-indexer/release-notes.md

Lines changed: 11 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -41,7 +41,15 @@ In order to upload a video from a URL, change your code to send nu
4141
var uploadRequestResult = await client.PostAsync($"{apiUrl}/{accountInfo.Location}/Accounts/{accountInfo.Id}/Videos?{queryParams}"null);
4242
```
4343

44-
## June 2022 release updates
44+
## July 2022 release updates
45+
46+
### Featured clothing insight (preview)
47+
48+
You can now view the featured clothing of an observed person, when indexing a video using Azure Video Indexer advanced video settings. With the new featured clothing insight information, you can enable more targeted ads placement.
49+
50+
For details on how featured clothing images are ranked and how to view this insight, see [observed people featured clothing](observed-people-featured-clothing.md).
51+
52+
## June 2022
4553

4654
### Create Video Indexer blade improvements in Azure portal
4755

@@ -150,7 +158,7 @@ Azure Video Indexer introduces source languages support for STT (speech-to-text)
150158

151159
### Matched person detection capability
152160

153-
When indexing a video through our advanced video settings, you can view the new matched person detection capability. If there are people observed in your media file, you can now view the specific person who matched each of them through the media player.
161+
When indexing a video with Azure Video Indexer advanced video settings, you can view the new matched person detection capability. If there are people observed in your media file, you can now view the specific person who matched each of them through the media player.
154162

155163
## November 2021
156164

@@ -167,7 +175,7 @@ For more information go to [create an Azure Video Indexer account](https://techc
167175

168176
### People’s clothing detection
169177

170-
When indexing a video through the advanced video settings, you can view the new **People’s clothing detection** capability. If there are people detected in your media file, you can now view the clothing type they are wearing through the media player.
178+
When indexing a video with Azure Video Indexer advanced video settings, you can view the new people’s clothing detection capability. If there are people detected in your media file, you can now view the clothing type they are wearing through the media player.
171179

172180
### Face bounding box (preview)
173181

articles/azure-video-indexer/toc.yml

Lines changed: 5 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -51,10 +51,13 @@
5151
href: language-identification-model.md
5252
- name: Observed people
5353
href: observed-people-tracing.md
54+
items:
55+
- name: People's detected clothing
56+
href: detected-clothing.md
57+
- name: People's featured clothing
58+
href: observed-people-featured-clothing.md
5459
- name: Matched person
5560
href: matched-person.md
56-
- name: People's detected clothing
57-
href: detected-clothing.md
5861
- name: Audio effects detection
5962
href: audio-effects-detection.md
6063
- name: Customizing content models

articles/azure-video-indexer/video-indexer-overview.md

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
title: What is Azure Video Indexer?
33
description: This article gives an overview of the Azure Video Indexer service.
44
ms.topic: overview
5-
ms.date: 06/09/2022
5+
ms.date: 08/15/2022
66
ms.author: juliako
77
---
88

@@ -61,7 +61,8 @@ The following list shows the insights you can retrieve from your videos using Az
6161
* **Animated characters detection** (preview): Detection, grouping, and recognition of characters in animated content via integration with [Cognitive Services custom vision](https://azure.microsoft.com/services/cognitive-services/custom-vision-service/). For more information, see [Animated character detection](animated-characters-recognition.md).
6262
* **Editorial shot type detection**: Tagging shots based on their type (like wide shot, medium shot, close up, extreme close up, two shot, multiple people, outdoor and indoor, and so on). For more information, see [Editorial shot type detection](scenes-shots-keyframes.md#editorial-shot-type-detection).
6363
* **Observed people tracking** (preview): detects observed people in videos and provides information such as the location of the person in the video frame (using bounding boxes) and the exact timestamp (start, end) and confidence when a person appears. For more information, see [Trace observed people in a video](observed-people-tracing.md).
64-
* **People's detected clothing**: detects the clothing types of people appearing in the video and provides information such as long or short sleeves, long or short pants and skirt or dress. The detected clothing is associated with the people wearing it and the exact timestamp (start,end) along with a confidence level for the detection are provided.
64+
* **People's detected clothing** (preview): detects the clothing types of people appearing in the video and provides information such as long or short sleeves, long or short pants and skirt or dress. The detected clothing is associated with the people wearing it and the exact timestamp (start,end) along with a confidence level for the detection are provided. For more information, see [detected clothing](detected-clothing.md).
65+
* **Featured clothing** (preview): captures featured clothing images appearing in a video. You can improve your targeted ads by using the featured clothing insight. For information on how the featured clothing images are ranked and how to get the insights, see [featured clothing](observed-people-featured-clothing.md).
6566
* **Matched person**: matches between people that were observed in the video with the corresponding faces detected. The matching between the observed people and the faces contain a confidence level.
6667

6768
### Audio insights

docfx.json

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1051,8 +1051,8 @@
10511051
"articles/azure-sql/virtual-machines/**/*.yml": "SQL Server on Azure VMs",
10521052
"articles/azure-video-analyzer/video-analyzer-docs/*.md": "Azure Video Analyzer",
10531053
"articles/azure-video-analyzer/video-analyzer-docs/*.yml": "Azure Video Analyzer",
1054-
"articles/azure-video-analyzer/video-analyzer-media-docs/*.md": "Azure Video Analyzer for Media",
1055-
"articles/azure-video-analyzer/video-analyzer-media-docs/*.yml": "Azure Video Analyzer for Media",
1054+
"articles/azure-video-indexer/*.md": "Azure Video Indexer",
1055+
"articles/azure-video-indexer/*.yml": "Azure Video Indexer",
10561056
"articles/azure-vmware/**/*.md" : "Azure VMware Solution",
10571057
"articles/azure-vmware/**/*.yml" : "Azure VMware Solution",
10581058
"articles/backup/**/*.md": "Azure Backup",

0 commit comments

Comments
 (0)