Object Recognition allows you to detect and track intricate 3D objects. It has been designed to work with toys (such as action figures and vehicles) and other consumer products.
Object Recognition can be used to build rich and interactive experiences with 3D objects. These experiences could be augmenting a toy with 3D content in order to bring it to life, overlaying a user manual on top of a consumer electronics device or leading a new employee through an interactive training process for a workplace device. Another simple application of Object Recognition is to unlock new in app content when a product is recognized.
Object Targets vs Image based targets
Object Targets are a digital representation of the features and geometry of a physical object. They are distinct from image based target types, such as Image Target, Multi Targets and Cylinder Targets that require the use of a planar source image. An Object Target is created by scanning a physical object using the Vuforia Object Scanner.
|Target Type||Target Source||Recommended Uses|
|Image based targets||planar images||publications, packaging, flat surfaces|
|Object Targets||feature scan||toys, products, complex geometries|
Object recognition may be used to build rich interactive experiences with rigid 3D objects. These experiences could be 3D content augmented on toys, instructional manuals overlaid on consumer products or simply new content unlocked when a product is recognized.
For Object Recognition to work well, the physical object should be opaque, rigid and contain few moving parts. The surface of the object should have contrast-based features. Pliable or deformable objects are not supported. Objects with articulating members are not supported as whole objects, but you can utilize the non-articulating regions of the object as an Object Target. Some good examples are toys such as action figures and vehicles.
Electronics and Machinery
Objects should be viewed indoors under moderately bright and diffuse lighting. To the extent possible, the surfaces of the object should be evenly lit and not contain shadows cause by other objects or people.
Working with Object Recognition
To enable Object Recognition in your app you will need to create an Object Target. You can add an Object Target to your app using the following workflow:
2. The Object Data file is uploaded to the Vuforia Target Manager where an Object Target is generated and can be packaged into a Device Database. A maximum of 20 Object Targets can be included in a Device Database.
3. The database is downloaded and added to a Vuforia Object Recognition project developed in Eclipse, Xcode or Unity. You can also use Object Targets in combination with other target types.
The Vuforia Object Recognition Sample project provides a pre-configured Object Recognition scene that you can use as a reference and starting point for your own Object Recognition apps. This How To article will show you how to add Object Targets to the sample and how to customize event handling for Object Recognition events.
How To Use the Vuforia Object Recognition Unity Sample
Object Recognition FAQ
What is the Vuforia Object Scanner?
The Vuforia Object Scanner is an app that allows you to scan and create object targets.
Is the Vuforia Object Scanner available for iOS devices?
The Vuforia object scanner does not support iOS devices at this time.
What devices does the Object Scanner app support?
The Vuforia Object Scanner is supported on the Samsung Galaxy S5 and Google Nexus 5 running Android version 4.2 and above. Using the app on other Android devices may not produce optimal results.
How many objects can I have in a database?
A Vuforia database can hold up to 20 object targets. If you want to recognize more than 20 objects in your app you can use more than one device database. See How To Load and Activate Multiple Device Databases at Runtime for managing multiple databases.
How many objects can I simultaneously recognize and track?
Vuforia allows your app to recognize and track 2 objects simultaneously.
How do I create an object target?
Can I recognize large objects, like a car or a building?
Object Recognition is optimized for objects that can fit on a tabletop and are found indoors.