Log in or register to post comments

Best Fusion Provider for Image Targets

February 25, 2019 - 10:39am #1

Our applicaton onIy uses image targets. I stumbled across a deprecation warning about FUSION_OPTIMIZE_IMAGE_TARGETS_AND_VUMARKS in the documentation and was wondering if there is any difference (in terms o quality) in recognition or tracking of image targets depending on the used fusion provider?

For example: Is native AR (ARKit and ARCore) via FUSION_PROVIDER_PLATFORM_SENSOR_FUSION better / worse compared to  FUSION_PROVIDER_VUFORIA_SENSOR_FUSION (VISLAM) when it comes to image targets?

Do i even need FUSION_PROVIDER_PLATFORM_SENSOR_FUSION when i only using image targets? Does it even make sense to activate it?

 

About Fusion API

 

AttachmentSize
Image icon fusion-apis.png320.23 KB

Best Fusion Provider for Image Targets

March 1, 2019 - 5:01am #5

Thank you very much for the detailed feedback. I highly appreciate it.

Best Fusion Provider for Image Targets

February 28, 2019 - 2:36pm #4

Hello,

bedrocks wrote:

1. Does this mean (if we only use image targets and no extended tracking), in theory we don't need a native provider (ARCore / ARKit) at all because detection and tracking is handled by Vuforia CV itself?

Correct. The Positional Tracking feature, as provided by Vuforia Fusion (through ARCore, ARKit or Vuforia VISLAM), is only used for Extended Tracking, Ground Plane and Model Targets.

bedrocks wrote:

2. Are there any settings to tell Vuforia it should exclusive concentrate on Image Targets and "forget" about "all the rest" e.g. model targets, smart terrain?

You can explicity set the FusionProviderType to VUFORIA_VISION_ONLY:

https://library.vuforia.com/content/vuforia-library/en/reference/unity/namespaceVuforia.html#afa43fb4756bd67edb0ea1bca50033dce

This will effectively disable Positional Tracking via Fusion. There are no APIs to disable features.

bedrocks wrote:

E.g. there is a Unity Setting which is part of the Vuforia Configuration called "Optimize Quality" vs "Optimize Speed". My naive assumption was that quality means more pixels (which probably means lower FPS) and speed means less pixels (which means more FPS). Does this setting has any relation to the image recognition task or is this only related to rendering (probably the camera background image)?

The Camera Device Mode is an abstraction of the Vuforia Engine API SelectVideoMode(): https://library.vuforia.com/content/vuforia-library/en/reference/unity/classVuforia_1_1CameraDevice.html#a8cd99944db68cd1b5709326042353c19

Your assumption is generally correct. Each Camera Device Mode has several settings related to it, including camera capture resolution, camera capture frame rate, and rendering resolution. The modes available and the device's performance when that mode is set (i.e. FPS) is dependent upon the device's capability.

bedrocks wrote:

3. Is there anything else (in the engine itself) i could take a look at to optimize the system for my use case?

The SDK is highly optimized for your use case. I cannot think of any other optimizations for your use case at this time.

Thanks,

Vuforia Engine Support

Best Fusion Provider for Image Targets

February 27, 2019 - 12:48am #3

Hello medabit,

thanks for your feedback and for the clarification.We don't use Extended Tracking because it doesn't work well with our use case.

Here are a few more questions so that we can better understand what the technology is capable of and what's it's boundaries.

1. Does this mean (if we only use image targets and no extended tracking), in theory we don't need a native provider (ARCore / ARKit) at all because detection and tracking is handled by Vuforia CV itself?

2. Are there any settings to tell Vuforia it should exclusive concentrate on Image Targets and "forget" about "all the rest" e.g. model targets, smart terrain?

E.g. there is a Unity Setting which is part of the Vuforia Configuration called "Optimize Quality" vs "Optimize Speed". My naive assumption was that quality means more pixels (which probably means lower FPS) and speed means less pixels (which means more FPS). Does this setting has any relation to the image recognition task or is this only related to rendering (probably the camera background image)?

3. Is there anything else (in the engine itself) i could take a look at to optimize the system for my use case?

Best Fusion Provider for Image Targets

February 25, 2019 - 4:28pm #2

Hello,

Vuforia Fusion is not used for the detection and tracking of Image Targets. It is used for Extended Tracking use cases, where the target is either not in view or too distant to be tracked.

The default setting is FUSION_PROVIDER_ALL, which means you do not need to specify the Fusion provider. Since it does not sound like Extended Tracking is one of your primary use cases, then it seems that the setting is irrelevant and you don't need to adjust it.

Thanks,

Vuforia Engine Support

Log in or register to post comments