API Guide

POST object-detection

POST https://nvision.nipa.cloud/api/v1/object-detection

This endpoint allows you to get free cakes.

Headers

Name	Type	Description
Authentication	string	ApiKey: Authentication token to track down who is requesting predictions.
Content-Type	string	Application/json

Request Body

Name	Type	Description
raw_data	string	Base64 encoded string of an image
configurations	array	List of configuration params corresponding to the service.

200 Predictions successfully retrieved.

{    
   "source_id" : "",
   "frame_id" : "",
   "service_id" : "",
   "detected_objects" : [
      {
         "bounding_box" : {
            "bottom" : 251,
            "top" : 167,
            "right" : 479,
            "left" : 361
         },
         "parent" : "electronic",
         "cropped_image" : "",
         "confidence" : 0.995199978351593,
         "name" : "tvmonitor"
      }
   ]
}

400 The request body is not conformed.

401 The API key is not valid, not defined, or revoked.

429 Request rate limit exceeded.

500 Internal server error.

Example JSON Request Body

{
    "raw_data": <<BASE64_ENCODED_IMAGE>>,
    "configurations": [
        {
            "parameter": "ConfidenceThreshold",
            "value": "0.1"
        },
        {
            "parameter": "OutputCroppedImage",
            "value": "false"
        },
        {
            "parameter": "OutputVisualizedImage",
            "value": "false"
        }
    ]
}

The configuration is different on individual service types. It is structured as a key-value mapping. A config name is defined in parameter field and the corresponding value is defined in value field in string format.

For object detection service, there are two available configurations as follows:

• ConfidenceThreshold: to define the minimum confidence score of the prediction results.

  • Value options: [0, 1]

  • Default: "0.1"

• OutputCroppedImage: to return cropped images from bounding box detections.

  • Value options: "true" or "false"

  • Default: "false"

• OutputVisualizedImage: to return drawn bounding box detections on raw image.

  • Value options: "true" or "false"

  • Default: "false"