Skip to content

Landmark Detection Activity

The Landmark Detection activity identifies popular natural and human-made structures within an image. It leverages Google Cloud Vision capabilities to analyze image content and return details about detected landmarks.

Field Description Requirement
Api key Google Cloud Vision API Key Required
Image path/url Google Cloud Storage URL of the image Optional
Base64 Base64 string of the image file Optional
Response variable name Variable name to store the HTTP response Required

Action Types & Examples

Get Detection Result

  • Format: string (JSON)
  • Example Result: {"responses":[{"landmarkAnnotations":[{"description":"Eiffel Tower","score":0.98,"mid":"/m/019_s"}]}]}

Implementation Examples

Field Setup - Api key: bb3c53c6-8515-4e34-97c8-8281de60972d - Image path/url: gs://cloud-samples-data/vision/ocr/sampleimage.jpg - Base64: /9j/4AAQSkZJRgABAQEAYABgAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMDAsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/2wBDAQMEBAUEBQkFBQkUDQsNFBQUF.../58x/8BX+R/9k= - Response variable name: getRespone

Execution Parameters - Output variable: getRespone - Result type: string (JSON)

Technical Notes

The activity requires either the Image path/url or Base64 field to be configured for successful execution. Detailed information about Google Cloud Vision detect landmark features can be found at Google Cloud Vision API Documentation.