Project Help Workflow Object Recognition

Hello,

I have done a lot of research but I think it is time to call in the experts to give me the best workflow to complete this.

I am going to give a general idea of what i want to achieve and where i am at.

My idea is to use augmented reality as an app for IOS, the concept is to have for example a generic "Printer" in real life, and when the app sees the printer, a 3D Human model appears on the screen doing some form of animation with a 3D model of a printer (or other object 'unimportant').

So let's just say i have the 3D models and animations, i could easily achieve this by just sticking a single image to the printer in real life on each object to have the animation play, but I do not want to do that, what i would like to do is to play the 3D animation from the point where the app sees the printer.

The issue is, i can't scan the printer as it don't fit on the a4 vuforia object scanner..

So i am now unable to do that, I thought of using a pre existing 3D model of lets say a printer, and do a model recognition, i know as it works on geometry this could be a method, the issue is that it was not recognised on app because obviously the 3d version is going to be slightly different than the real version.

The third method was to use a video background to play a video but i am not interested in that either.

I have considered three methods as seen on top but not really sure what to do now that i am stuck.

The object target was my best choice but the size of the paper to scan it in is too small.

Keep in mind when i say "printer" i am talking about doing it on other models that are medium size and are all bigger than the paper.

Do you have any ideas about to do this type of thing with medium sized objects, I would love to know!

Any links or informational tips would greatly be appreciated, thanks.

Hello,

Thanks for the detailed description.

JarradMorden wrote:

The issue is, i can't scan the printer as it don't fit on the a4 vuforia object scanner..

Updated versions of the Object Scanner target can be found here: https://developer.vuforia.com/forum/object-recognition/printing-large-format-version-vuforia-object-scanner-target

These PDFs are scalable as they contain a vectorized image, instead of a bitmap. This means you can now print it to any scale without degradation.

There are many factors that can affect the tracking performance of a Object Target, both during the scanning process and when running an app. Most issues with Object Targets can be traced to the creation of the .od file using the Vuforia Object Scanner. Be sure to follow the scanner app instructions: https://library.vuforia.com/articles/Training/Vuforia-Object-Scanner-Users-Guide, paying close attention to step #8 in the article.

When creating the .od file, was the model scanned in an environment that was free of background details which may have introduced features that were not part of the model? Scanning in 'cluttered' environments can introduce false detection/tracking points.
When creating the .od file, were there any specular reflections on the model introduced by environmental lighting? Scanning objects that have reflective surfaces under direct lighting can introduce areas with no detection/tracking points.
Are you using the recommended devices referenced on the tool download page?: https://developer.vuforia.com/downloads/tool

In our labs, we utilize four primary strategies for creating an optimal Object Target scanning environment:

All background surfaces are colored at 18% gray. An easy, off-the-shelf solution is to buy bed sheets near this color and drape everything in the environment that could be seen by the scanning device's camera.
No direct lighting. We use light boxes and/or diffusers to eliminate direct lighting upon the object and minimize any spectral reflections.
Utilize a 360 turntable to re-orient the device. This is especially helpful when you've set your environment to near ideal conditions within a limited area. You can spin the model and scan in 360 degrees without having to move around it.
Be sure that the environment in which you’re testing (via the Object Scanner app ‘test mode’) is the same in which you’re verifying tracking (via the sample code). Environmental factors such as lighting, shadows, spectral reflections, etc. can negatively affect tracking performance, so awareness of how the environment is interacting with your model is important for qualifying performance.

Lastly, be sure to use meters and the default scale as this can also impact the feature's accuracy and performance.

Good luck.

-Vuforia Engine Support

Project Help Workflow Object Recognition

Delete Message

Delete Conversation

Login

Forgot Password