Model Targets Supported Objects & CAD Model Best Practices

Supported Object Types

The Vuforia Model Targets Feature provides robust recognition and tracking for supported objects and use cases.

The types of supported range from toys to full-sized vehicles, to architectural landmarks and to medical, manufacturing and industrial equipment.

In the following sections we highlight the properties of physical objects that are supported with Vuforia's Model Target technology. Good and bad examples are shown to demonstrate the specific quality differences. These images are exemplary 
and shall only act as indication. You may verify your specific use-case to comply to these recommendations.

Use-cases stretching the limits of the technology - such as using ModelTargets on moving or articulated objects, and objects that are shiny or transparent are currently not supported robustly.

Fixed Position in Space

Objects are assumed to be static. They need to remain static in the environment after having been detected. The user can move around the object with the AR-devicee but should not move the object itself. If you need to support movement or replacement of objects, stop and then restart tracking after object has moved in your app.

 

Fixed Postion

Colored or Patterned Surface 

Objects with colored or patterned surfaces typically work better. Objects in a single uniform color are difficult to track, though they can be reliably detected. Some variation in surface appearance is required to distinguish the object. For this reason, a pure white object on a pure white background or pure black objects on very dark backgrounds may not work well. Sometimes 3D printed objects made from a single-color material might be difficult to track.

NOTE: The color of the physical model must not exactly follow the color in the CAD model used for target generation. One Model Target dataset may be used to detect and track color variations of the same product.

 

Vuforia Image

Sufficient Geometric Detail - Complex Enough Model

Geometric complexity is key to distinguish an object from other shapes in the environment. Simple shapes such as cubes, spheres, symmetric objects, or very elongated simple shapes may be easily confused with other objects in the user’s setting.

Try to base your experience on products or objects that have enough sharp edges, dents, bulges, etc.

 

Vuforia Image

Non-flexible and Rigid

While the Model Target tracker can tolerate some deviation between physical and digital model - e.g. one variant of a product has some small attachment that is not present in another, or some part was left out from the CAD-model consciously because it's known to move (see above) - expect that objects that articulate and/or flex may fail to be detected or tracked effectively!

 

Articulation

Matching CAD-model

Physical objects should have the exact same shape and size as their 3D CAD model used for target generation. It is important to have a strong overlap for the robustness of the experience.
While wrongly scaled objects might be detected, tracking performance will be sub-par if metric scales don't correspond between physical and digital object.

For practical reasons - since sometimes CAD models just don't represent the physical object 1:1 - the Model Target technology is capable to tolerate up until 20% of deviation between real and virtual object as a compromise.

 

Patterned Surface

CAD Model Best Practices

While the previous section provided advice on how to select physical objects that work well with the Model Targets feature, this section provides recommendations for how to best prepare the corresponding CAD data.

In general, the CAD model used as input for the Model Target Generator should

  • have a maximum of 400,000 polygons or triangles; and
  • contain a maximum of 10 parts; and
  • contain a maximum of 5 textures; and
  • use a right-hand coordinate system.

These hints have been compiled based on common problems encountered with CAD models. Note that due to the large variety of CAD software available, with numerous possible generation pipelines, it's difficult to provide solutions that work in all cases. Therefore the following advice is by necessity somewhat generic, and specific models may have still particular issues. Feel free to get in touch via the forums if the Model Target Generator isn't working properly for your particular model.

Some further examples of what can make a CAD model unsuitable for Model Target usage, and recommendations for potential fixes follow:

Large Holes

Models sometimes tend to have cracks in their polygonal representation. This typically results from wrong tesselation, simplification, or combination mismatches. Try to avoid these as such holes create unnecessary, false details on the object that create computational overhead and potentially lead to false detections. Tip: Modern CAD software packages can verify models prior 3D printing for holes and cracks, such tool can be helpful to verify your model prior working with Vuforia.

 

Vuforia Image

Missing Parts

During the conversion pipeline some parts of a model might be corrupted, have wrong (transparent) material properties, or simply be missing in an assembly filter. Visually compare the loaded CAD model in the Model Target Generator to contain all your desired parts, visually matching with the physical object to be augmented.

 

Vuforia Image

Incorrect Normals

Normals facing wrong direction - away from physical surface normal - might cause mesh elements not to render leading to diverse side-effects. Additional edges, visible inside objects of a complex model, screen-door effects on surfaces, etc. can create wrong visual representation of the CAD model and result in low detection and tracking performance. Incorrect normals can also yield apparently missing parts, see above section. Visually verify integrity of normal distribution, some packages provide tools to conform normals.

 

Vuforia Image

Missing Color Information or No Texture

It is recommended to have a color - not necessarily a real color - associated with each part, unless the object is a 3D printed from a single material. It is also helpful to add textures to your model if those add visual fidelity - resembling the physical object. These can be surface patterns, label, prints or flat elements - such as gauge-backplates.

Such details help the Vuforia Engine to extract the necessary detail from the geometry better to improve detection an d tracking. The final detection and tracking performance depends on a lot of run-time factors such as lighting intensity and color though. The Model Target Generator will provide a warning if such detail is missing.

 

 

Vuforia Image

As indicated in the previous section it is good practice to use different colors on parts indicating different materials or surface properties of the real object. While Model Targets is designed to detect objects by shape, giving additional information on the materials will often greatly improve detection robustness. Note that there is no need for model colors to match the colors of the real object. Colors can also be used to indicate different parts with small gaps in between that are strongly visible in reality but different to extract from a rendered view. Examples are e.g. gaps between the body and the door of a car. If possible, avoid single-color models and file formats that can’t transport color information such as STL.

Vuforia Image

Wrong Texture Information

Model Targets is designed to be used with CAD-like models that use only few colors to indicate different materials. Please avoid photorealistic textures such as with baked in lighting from game-models or photogrammetry 3D-scans. If you need to use photogrammetry 3D-scans, please remove the texture before importing into the MTG!

 

Vuforia Image

Learn More

Model Targets Overview

Model Targets Generator User Guide

Trained Model Target Datasets

3D Printing Instructions for the Viking Mars Lander