Soracom Flux
Object Detection Action
The Object Detection Action detects the following objects in a still image and sends the object information to the destination channel.
- Person
- Car
- Bus
- Truck
- Cat
- Dog
Information about other detected objects will be also returned along with their location in the image and confidence score. For details, refer to Output Data of the Action.
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, please refer to Use Expressions in Actions.
Config
Configure the operation of the Object Detection Action.
- Image URL: Specify the URL of the still image to be used for 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 object detection on the file uploaded to Soracom Harvest Files.
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
The output data of the Simple Object Detection Action is as follows.
{
"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"
}
]
}
The attributes are as follows:
Attribute | Description |
---|---|
person | Number of detected people. |
car | Number of detected cars. |
bus | Number of detected buses. |
truck | Number of detected trucks. |
cat | Number of detected cats. |
dog | Number of detected dogs. |
objects[] | Information about the objects detected by the Simple Object Detection Action. |
objects[].location | The position of the detected object within the still image. |
objects[].score | Confidence score indicating the accuracy of the detected object. |
objects[].label | Detected object label. |
objects[].ts | Date and time when the object was detected. |