Soracom Flux

Simple Object Detection Action

The Simple Object Detection Action detects objects in a still image and sends the object information to the destination channel.

By default, the action counts the number of detected objects for the following 6 classes:

• Person
• Car
• Bus
• Truck
• Cat
• Dog

In addition, the action detects all supported object classes and returns their information in the objects array. For details, refer to Output Data of the Action.

When Target Object Classes is configured, the action counts and detects only the specified object classes. For details, refer to Target Object Classes.

Configuration

Condition

In the Action Condition section, you can specify the conditions under which the action will be executed using the values (Message or Context) from the event source to the channel. For more details on the expressions you can input, refer to Use Expressions in Actions.

In this input field, you can enter expressions representing data related to the trigger that starts the Flux application (e.g., event.payload.temp) or data related to the channel where the action is added (e.g., payload.temp).

Config

Configure the operation of the Simple Object Detection Action.

Image URL: Specify the URL of the still image to be used for simple object detection. For example, if you are using the Soracom Harvest Files event source in the same Flux App, you can specify ${event.payload.presignedUrls.get} to perform simple object detection on the file uploaded to Soracom Harvest Files.

• In this input field, you can enter expressions representing data related to the trigger that starts the Flux application (e.g., ${event.payload.temp}) or data related to the channel where the action is added (e.g., ${payload.temp}). For details on supported expressions, refer to Action Config Expressions.

Target Object Classes

Specify the object classes to detect in the image. If no selection is made, all supported object classes will be targeted for detection. You can select multiple class labels.

Output

Configure how to handle the output data of the action. Refer to Enable Republishing of Action Output for more details.

Output Data of the Action

By default, the output data includes the count for each of the 6 default classes and the objects array containing all detected objects regardless of class. The following example shows a person and a cup detected in the image:

{
  "person": 1,
  "car": 0,
  "bus": 0,
  "truck": 0,
  "cat": 0,
  "dog": 0,
  "objects": [
    {
      "location": [
        0.42561606168746946,
        0.3883926073710124,
        0.5880238652229309,
        0.8953371047973633
      ],
      "score": 0.6473677158355713,
      "label": "person",
      "ts": "2024-06-17T05:28:24Z"
    },
    {
      "location": [
        0.3454461991786957,
        0.6387763867775599,
        0.39976382851600645,
        0.739234521985054
      ],
      "score": 0.5285048484802246,
      "label": "cup",
      "ts": "2024-06-17T05:28:24Z"
    }
  ]
}

When Target Object Classes is configured (e.g., truck), the action counts and detects only the specified classes. The objects array contains only objects matching the specified classes. For example, when a truck is detected:

{
  "person": 0,
  "car": 0,
  "bus": 0,
  "truck": 1,
  "cat": 0,
  "dog": 0,
  "objects": [
    {
      "location": [
        0.04083414,
        0.21190794,
        0.4107799,
        0.8861815
      ],
      "score": 0.91171336,
      "label": "truck",
      "ts": "2026-03-16T23:39:13Z"
    }
  ]
}

When no objects matching the specified class labels are detected:

{
  "person": 0,
  "car": 0,
  "bus": 0,
  "truck": 0,
  "cat": 0,
  "dog": 0,
  "objects": []
}

The attributes are as follows: