Model Targets use Guide Views for detection and initializing tracking based on a Guide View’s angle and distance relative to the object. The Guide View is generated together with the Model Target database in the Model Target Generator desktop tool provided by Vuforia.
There are two types of Guide Views that can be created for a Model Target: Guide View and Advanced (Guide) View. For each Model Target, one or more Guide Views can be created to help detection and tracking the object. A Guide View is created instantly alongside the Model Target and an Advanced View requires you to upload the Model Target for training. See Advanced Model Target Databases for details; see also the summaries below:
- Standard Model Target databases can have one model with one or multiple Guide Views which can be switched between manually. These types of Guide Views are displayed to help position the user and camera so that tracking of the object can start. The position that the Guide Views represent have some tolerance on how exact users need to match the outline with the object.
- Advanced Model Target databases can contain one to multiple Model Targets that are trained using a deep learning process. Each Model Target in the database can contain one or more Advanced Views that support recognition up to a 360° range around the object or with other presets. See Advanced Views for details on setting up an Advanced View.
For a demonstration of how Guide Views work within a typical Model Target application, see Introduction to Model Targets in Unity, the Core Samples, and the Model Target Test App User Guide.
A Guide View is the visual presentation of the object from a defined angle and distance. Users match the outlines with the object to initiate tracking of the object. Having one or multiple Guide Views for a Model Target depends on the use case, but a single Guide View is enough to maintain tracking of the object on its other sides as well.
Choosing a Good Guide View for a Model Target
Guide Views for Model Targets are created from a position and angle that represents how a user should approach an object. Guide Views allow for some tolerance where the object will also be recognized even if the user approaches from an angle or distance that deviates from the created Guide View position. Those tolerances are listed below:
- About +/- 45° horizontally with respect to the center of the Guide View.
- About +/- 15° to the vertical top or bottom from the selected position.
- About 15% closer or further away from the object, depending on the shape of the object.
- About +/- 10° of rotation around the Guide View viewing direction (roll).
Guide View position
For a stable detection and tracking of your object, choose a Guide View position where you have a diagonal view, i.e., an angle where two or three sides of the object can be seen at the same time, as shown below in left image. Avoid a position that presents a front-to-parallel view onto the object, i.e., do not choose a view that is “square on” to one side of the object as seen in the image below on the right side. In addition, try to avoid a Guide View position that makes the object appear to have many parallel lines/edges.
Favorable diagonal Guide View alignment
Undesirable Guide View with less object visibility and parallel lines.
TIP: Use the navigation buttons in the Model Target Generator in the left side of the window to navigate around the object when you are choosing your Guide Views.
If your object is very large, it may be difficult to find a Guide View that is near enough to the object and still shows the entirety of the object. If this is the case, choose a Guide View that captures the object from an angle with the most unique features. Avoid sides of the object that has large flat surfaces, and instead find an angle of view where unique shapes on the object are more apparent.
Create Guide Views in the MTG
First Create Guide View, in the next menu, select between Landscape or Portrait modes for handheld devices, or head display for digital eyewear devices. This setting takes into account the correct field-of-view of the device. Use the dashed-line frame displayed in the MTG to set up the Guide View’s desired position fitting your use-case. The rendered Guide Views on screens are device agnostic - but the render can be tuned with the viewport settings.
See How to Create a model Target for a step-by-step guide.
Guide View customization
You may also consider using your own 2D image or graphics to render as a Guide View. If you use your own image, for correct placement, we recommend that you scale the image such that the longer side of the image has the same length as the long side of the camera image. Alternatively, you can use the view intrinsic parameters (provided in the Guide View instance) in combination with the current camera calibration or device screen resolution to adjust the scale/aspect ratio of the image.
You can also render a 3D modelrepresenting the object as it appears from the Guide View pose. You can use the view extrinsic parameters provided on the Guide View instance in combination with the current camera calibration to do this.
NOTE: If you are working with stereo eyewear such as the HoloLens, you are recommended to render the Guide View as a 3D model.
Multiple Guide Views
It is possible to add multiple Guide Views to a single Model Target and then switch between these different Guide Views at runtime. For example, you might have a service manual app with repair guides for various parts of a machine, and you want the user to be able to select which part they want to look at from an in-app menu. See the Model Targets in Unity and Model Targets API Overview for details on how to switch between Guide Views at runtime.
Multiple Guide Views can be added manually after creating the first view by repositioning the camera view and clicking Add View. Do this one-by-one by for each individual Guide Views you wish to have. You can re-adjust a Guide View by clicking the icon located on the top right of the preview image of the Guide View.
See also Advanced Views for a guide to set up Advanced Views for Model Targets.