tencent cloud

Human Recognition
Download PDF
Last updated: 2025-09-09 20:02:22
Human Recognition
Last updated: 2025-09-09 20:02:22
Download PDF

Feature Overview

Tencent Cloud DataV provides human body recognition and outputs video images through the AIBodyRecognition interface, including their positions (rectangle frames) and confidence degrees.
Note:
This interface belongs to a GET request, uses a synchronous request method, and requires carrying a signature. For specific signature settings, please see Request Signature.

Authorization Description

When using with a sub-account, the ci:CreateBodyRecognitionJob permission is required. For details, see CI action.

Service Activation

Using this feature requires enabling Cloud Infinite in advance and binding a bucket. For details, see Bind Bucket.
Use this feature requires enabling AI Content Recognition service in advance via console or API. For details, see Enable AI Content Recognition Service.

Use Limits

When using this API, please first confirm the relevant restrictions. For details, see Usage Limits.


Request Syntax

GET /ObjectKey?ci-process=AIBodyRecognition&detect-url=<detect-url> HTTP/1.1
Host: <BucketName-APPID>.cos.<Region>.myqcloud.com
Date: GMT Date
Authorization: Auth String
Note:
Authorization: Auth String (See Request Signature document.)

Request Content

Parameter Name
Description
Type
Required or Not
ci-process
Cloud Infinite processing capability Human recognition fixed as AIBodyRecognition
String
Yes
ObjectKey
object filename, for example picture.jpg
String
No
detect-url
You can handle any publicly accessible image link by filling in detect-url. If detect-url is not specified, the backend will default to processing the ObjectKey. If detect-url is filled in, the backend will process the detect-url link, and there is no need to fill in the ObjectKey.
example for detect-url: http://www.example.com/abc.jpg, needs to be url encoded, processed result is
http%25253A%25252F%25252Fwww.example.com%25252Fabc.jpg
String
No

Request header

This API only uses common request headers. For details, see Common Request Headers documentation.

Request body

This request has no request body.

Response

Response Headers

This API only returns the public response header. For details, see Common Response Headers documentation.

Response Body

The response body is returned as application/xml. The specific data content is as follows:
Node Name (Keyword)
Parent Node
Description
Type
RecognitionResult
None.
Container for saving Logo recognition results
Container
The content of Response
Node Name (Keyword)
Parent Node
Description
Type
Status
RecognitionResult
Human recognition result. 0 indicates no recognition, 1 indicates recognition.
Int
PedestrianInfo
RecognitionResult
Human recognition results, possibly multiple.
Container
LogoInfo node content:
Node Name (Keyword)
Parent Node
Description
Type
Name
PedestrianInfo
Recognition type, default for human recognition: person
String
Score
PedestrianInfo
Confidence degree of human body, value range [0-100]. Higher value indicates higher probability.
String
Location
PedestrianInfo
Coordinates of human body detected in figure
Container
Location node content:
Node Name (Keyword)
Parent Node
Description
Type
Point
Location
Coordinate point of human body (X coordinate, Y coordinate)
String

Example

Request

GET /?ci-process=RecognizeLogo&detect-url=<detect-url> HTTP/1.1
Host: examplebucket-1250000000.cos.ap-chengdu.myqcloud.com
Date: <GMT Date>
Authorization: <Auth String>

Response

HTTP/1.1 200 OK
Content-Type: application/xml
Content-Length: 414641
Date: xxxxxx
Server: tencent-ci
x-cos-request-id: NTk0MjdmODlfMjQ4OGY3XzYzYzhfMjc=

<RecognitionResult>
    <Status>1</Status>
    <PedestrianInfo>
        <Name>person</Name>
        <Score>90</Score>
        <Location>
            <Point>162,266</Point>
            <Point>162,716</Point>
            <Point>392,716</Point>
            <Point>392,266</Point>
        </Location>
        <Name>person</Name>
        <Score>89</Score>
        <Location>
            <Point>682,162</Point>
            <Point>682,479</Point>
            <Point>783,479</Point>
            <Point>783,162</Point>
        </Location>
    </PedestrianInfo>
</RecognitionResult>

Was this page helpful?
You can also Contact Sales or Submit a Ticket for help.
Yes
No

Feedback