Start a new topic

Instant tracking 3D space recognition

First of all, thank you for such impressive feature - Instant tracking!

I have some questions about features of this feature.

1. Is it (or will be) possible to detect full 3D environment, for example stairs (walls and so on) for accurate object positioning (for example painting on the wall or bouncing ball down the stairs)?

2. Is it (or will be) possible to recognise 3D object from real world, like target images?

3. Is it (or will be) possible to "record" some environment (like 3d map), for loading it later for instant tracking 3D scene in EXACT location (for example exact room). A part of such feature were in demo video - 3d map of office space.

Or maybe this features will be in future releases?

Hi there,

First of all thank you very much for your feedback. Regarding your questions, these are functionalities that will be included in our 3D Object Recognition feature. I cannot tell you exactly when this will be available for release but we are planning it this year so I will keep you updated!



hi, I tried the instant tracking example and it doesn't seem to work..I can't even see the cross hair when the camera is turned on...even when i click on the initialization button..nothing changes.can you please help.thanks

Hello Saher,

Could you please send more details regarding your issue by providing the following information:

- Which version of the SDK are you using?
- Are you using the JS API?
- Are you using any of our Extensions?
- When you say that it is not working, what exactly is not working? Are you receiving an error and if so please send the crash log.
- What device does this happen with (os Version and model)?
- is this happening with the sample app?
- Send exact steps to reproduce this issue and a video so we can check how we can reproduce this issue




Great news for you as today we launched SDK 7, which includes your feature request, “Object Recognition”. In a nutshell, SDK 7 introduces:
  • Object Recognition
  • Multiple Image Target Recognition
  • Hit-testing API for SLAM
  • Instant tracking improvements
  • Extended recognition range

significantly expands Wikitude’s SLAM technology by adding object recognition and tracking capabilities to its feature set. These features enable brands and enterprises to build augmented reality experiences using a variety of real-world objects, such as toys, sculptures, architectural models, product packaging, industrial machines and more.

The workflow is simple: record a video of your object, upload it to the Wikitude Studio Manager and create your AR experience as desired. Object recognition technology creates an additional touch point to interact with users, allowing real time and 360 degrees augmented reality experiences around real world objects.


Check out this blog for a developer insight and this tutorial to see how you can create your first 'Object Target Collection'. You can download the new SDK 7 directly from our Download page. Enjoy our new cool features ;)




I am confused as to how v7.1.0 addresses the original question. Please advise how we are supposed to detect a 3D room in v7.1.0.  Per the original post:

1. Is it (or will be) possible to detect full 3D environment, for example stairs (walls and so on) for accurate object positioning (for example painting on the wall or bouncing ball down the stairs)?

As far as I have read we can rotate the instant tracking plane to detect a wall,ceiling or floor, but that does not help is understand where the wall or floor ends in order to properly map the room.

We are researching AR solutions for Xamarin for 3D space mapping and so far it seems Wikitude does not support our needs.  Please correct me if I'm wrong.

Thank you!



Thx for reaching out. It sounds there is a feature mix up -> the instant tracking feature now allows to change the tracking plane to vertical / horizontal. This allows you to work with our markerless AR tracking feature.

If you wish to work with Object Recognition you'll need to record one specific object for the recognition and tracking. The Object recognition feature isn't supposed to do room tracking.

I hope this helps. Should you need anything further, just let me know anytime.




Really grateful of wikitude for providing us with Instant Tracking Feature.
Th issue I am facing is that on initialization the instant tracking module does not detect the ground plane and selects any random plane. Considering my problem statement I want the module to detect the ground plane and augment my model on it. Is there any way by which I can restrict the module to detect the ground plane only?

SDK version : WIkitudeSDK Unity 7.2.0
Os version : Android Oreo
Device Model: Mi A1 & One+ 2


Instant Tracking by default favors placing the augmentations on the ground. I would recommend that you refer to the documentation here to see how you can adjust the 'deviceHeight' property.



Login or Signup to post a comment