Object detection-OpenSearch(Open Search)-阿里云帮助中心

Detects and identifies one or more objects in an image for computer vision applications such as intelligent surveillance, autonomous driving, and image search.

Service name	Service ID	Description	API QPS limit
object detection service	ops-object-detect-001	A multi-object detection model developed by the Alibaba Cloud OpenSearch-AI team. Detects multiple independent objects in an image and returns a bounding box and confidence score for each. Extracts objects from complex scenes as input for downstream tasks, helping eliminate interference from backgrounds or other objects when used with embedding and reranking models.	20 Note To request a higher API QPS limit, submit a ticket to technical support.

face detection service	ops-object-detect-face-001	Automatically detects and locates one or more faces in an image. Ideal for applications such as intelligent surveillance and image search.

Prerequisites

Get authentication credentials

The AI Search open platform requires an API key for authentication. For instructions, see Get an API key.
Get the service endpoint

You can call the service via the public network or a VPC. For details, see Get the service endpoint.

Request details

General notes

The request body cannot exceed 8 MB.

HTTP method

POST

URL

{host}/v3/openapi/workspaces/{workspace_name}/image-object-detection/{service_id}

Parameters:

host: The service endpoint. For details, see Get a service endpoint. The public API domain provides public network access, and the internal API domain provides access from within the same region (including from a VPC). Both endpoints support HTTPS.
workspace_name: The name of your workspace, such as default.
service_id: The ID of the built-in service, such as ops-object-detect-001.

Request parameters

Header parameters

Parameter	Type	Required	Description	Example
Content-Type	String	Yes	The content type of the request. Must be `application/json`.	application/json
Authorization	String	Yes	Your API key for authentication. Must be prefixed with `Bearer` .	Bearer OS-d1**2a

Body parameters

Parameter

Type

Required

Description

Example

service_id

String

Yes

The service ID. The value must start with ops-.

ops-object-detect-001

image

Object

Yes

The image to process. You must provide the image by using one of the following parameters:

url: A publicly accessible URL of the image.
content: The image file content, encoded as a base64 string.

{
 "url":"http://example.com/image.jpg"
}

Response parameters

Parameter	Type	Description	Example
request_id	String	A unique request identifier generated by the system.	A5B25952-4406-45BF-99EC-E8020246****
latency	Float/Integer	The request latency, in milliseconds (ms).	10
usage.image	Integer	The number of images processed.	1
result.objects	List<ImageObject>	A list of the detected objects.	`[ { "confidence": 0.8, "location": { "X" : 228, "Y" : 240, "height" : 430, "width" : 678 } } ]`

ImageObject

Parameter	Type	Description	Example
confidence	Float	The detection confidence score, ranging from 0.0 to 1.0. Higher values indicate greater confidence.	0.4017
location	Object	The bounding box coordinates of the detected object.
location.width	Integer	The width of the bounding box, in pixels.	176
location.height	Integer	The height of the bounding box, in pixels.	188
location.Y	Integer	The y-coordinate of the top-left corner of the bounding box.	560
location.X	Integer	The x-coordinate of the top-left corner of the bounding box.	37

Sample request (cURL)

curl --location 'http://****-hangzhou.opensearch.aliyuncs.com/v3/openapi/workspaces/default/image-object-detection/ops-object-detect-001/' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
    "image":
    {
      "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250408/syuvxh/%E7%89%A9%E4%BD%93%E5%AE%9A%E4%BD%8D.png"
    }
}'

Sample response

Successful response

{
  "request_id": "138611ad4a03f620a1cdb2904768d286",
  "latency": 216,
  "usage": {
    "image": 1
  },
  "result": {
    "objects": [
      {
        "confidence": 0.4017,
        "location": {
          "width": 176,
          "height": 188,
          "X": 37,
          "Y": 560
        }
      },
      {
        "confidence": 0.3805,
        "location": {
          "width": 191,
          "height": 200,
          "X": 133,
          "Y": 752
        }
      },
      {
        "confidence": 0.3290,
        "location": {
          "width": 175,
          "height": 183,
          "X": 359,
          "Y": 663
        }
      },
      {
        "confidence": 0.2955,
        "location": {
          "width": 984,
          "height": 897,
          "X": 16,
          "Y": 8
        }
      },
      {
        "confidence": 0.2613,
        "location": {
          "width": 172,
          "height": 174,
          "X": 516,
          "Y": 559
        }
      },
      {
        "confidence": 0.2573,
        "location": {
          "width": 360,
          "height": 228,
          "X": 665,
          "Y": 704
        }
      },
      {
        "confidence": 0.2419,
        "location": {
          "width": 139,
          "height": 170,
          "X": 248,
          "Y": 388
        }
      },
      {
        "confidence": 0.1644,
        "location": {
          "width": 173,
          "height": 205,
          "X": 815,
          "Y": 507
        }
      },
      {
        "confidence": 0.1134,
        "location": {
          "width": 140,
          "height": 122,
          "X": 440,
          "Y": 446
        }
      }
    ]
  }
}

Status codes

For details, see the AI Search Open Platform Status Codes.