Skip to content

Cloud Image Recognition

The Vuforia Cloud Image Recognition service is an enterprise-class Image Recognition solution that enables applications to recognize and track millions of Image Targets. Cloud Image Recognition is available as a Cloud Image Recognition Add-on and different tiers of Cloud Image Recognition Plus Add-ons. Usage is determined by the total number of image recognitions, or "recos", per month your app performs. Each reco is counted when a target is matched.

Applications for Cloud Image Recognition

The Vuforia Cloud Image Recognition service is ideal for apps requiring many targets or targets that need to be updated frequently. Cloud Image Recognition is suitable for:

  • Publications -- Catalogs, magazines, newspapers, etc.
  • Retailers -- Product visualization, in-store traffic generation, etc.
  • Advertisers -- Multi-branded content, coupons, promotions, etc.
  • Product Recognition -- Wine labels/bottles, cereal boxes, etc.

Leverage the following benefits of Cloud Image Recognition for your product and services:

  • Scalability: More than one million targets can be used in an app.
  • Flexibility: Integrate with existing content management systems (CMS).
  • Time to Market: Deliver real-time, dynamically changing content and accelerate time to market.

Deploy and manage your Cloud Image Recognition databases in two ways:

Prerequisites

Supported formats

The Target Manager and the VWS API support planar, 2D Image Targets for Cloud Image Recognition. Images used for Cloud Image Recognition must follow the same guidelines as Image Targets.

Please refer to Image Targets for more information and the best practices for creating well-tracking Image Targets for Cloud Recognition.

Supported licenses

  • All plans can be extended with the Cloud Image Recognition Add-ons. Each plan supports, by default, up to 1,000 recos per month on up to 1,000 images.
  • Cloud Image Add-on extends recos to 10,000 per month on up to 100,000 images.
  • Cloud Image Plus Add-on supports over 10,000 monthly recos on more than 100,000 images.

Access Keys

Configure the application with Cloud Database client keys, which consist of an access key and a secret key. The Client Access Keys and the Server Access keys are available in the database created in the Target Manager. Please refer to Vuforia Web Services for more details on the Access keys.

Cloud Image Recognition Databases

Create the Cloud Database

You can use the Target Manager to upload prepared images and any optional metadata associated with an image.

See the step-by-step guide on How to Work with Cloud Databases and Comparison of Device and Cloud Databases to get started.

Create the cloud database via the VWS

In cases where you already have your own CMS, you can use the VWS API to query the cloud database, upload images, add metadata, and much more. However, a Cloud Database must still be created with the Target Manager.

See Vuforia Web Services and How to Use the VWS API to get started.

SDK Workflow

To start with Cloud Recognition, see the Unity Core sample and Working with Cloud Image Recognition in Unity to learn how to handle cloud reco events and retrieve an image's metadata.

Cloud Image Recognition in native apps uses the VuCloudImageTargetObserver, which manages query execution and query results handling. You can only associate one cloud database per application.

See Cloud Image Recognition API Overview for native development.

Cloud Image Recognition Usage

In the Plan & Licenses tab, in the details of a license, a report on your app's user activity indicates how many Cloud Image recos have been executed as a proportion of the app's monthly reco limit.

The app usage bar is color-coded to indicate when you are approaching the maximum monthly usage for the plan associated with your app. If the bar is orange or red, your usage is approaching the maximum, and you should determine whether you will need to move to a plan that supports greater usage.

For more information on Cloud Image Recognition counts, please see Counting Cloud Image Recognition Events.

Cloud Image Recognition Metadata

A Cloud Image Target can have metadata associated with it. A target's metadata can be information and data on the image with a size limit of up to 1 MB per Image Target. Use the metadata to store additional content that your application can process.

Data stored in metadata

For example, your application may use the metadata to store the following items:

  • Display a text message when the target is detected. For example, "Hello, I am your cloud Image Target XYZ. You have detected me!"
  • A URL string, for instance, http://my_server/my_3d_models/my_model_01.obj, that points to a custom network location that you own and have content stored in, such as a 3D model, a video, an image, or any other custom data. For each different Image Target, your application could then use such a URL to display or download the specific content.

  • Some custom string text that your application can process and use to perform specific actions. Your metadata could also contain text to represent an object in JSON format, for example:

    1
2
3
4
5
    {
  "Name": "John",
  "Age" : "35",
  "Address": "10, Vuforia Avenue"
}

  • A complete 3D model, not just the URL pointing to a model on a server but the model itself. For example, the metadata could embed an OBJ 3D model, provided the size does not exceed 1 MB.

  • You can also store metadata containing the URL of a Unity Asset Bundle associated with the specific target (for instance, representing a 3D model or other Unity assets).

See AssetBundles to Package Augmentations in Unity for details on AssetBundles.

See How to Use Cloud Recognition for examples of retrieving the metadata associated with an Image Target.

Next Steps

Working with Cloud Image Recognition in Unity

Cloud Image Recognition API Overview

Working with Cloud Databases

Comparison of Device and Cloud Databases

Counting Cloud Image Recognition Events

Cloud Web API

Vuforia Web Services

Cloud Targets Web API

How to Perform an Image Recognition Query