Log in or register to post comments

Object Detection on Simpler and/or Smaller Objects

October 25, 2018 - 7:42am #2

Currently I've been having issues with some objects and I'd like to know if there's a better alternative to address this kind of cases:

 

- Glossy mugs (I tried to create a 3D Target after properly scanning it and it couldn't detect it, then I was going to try it as a cylinder but it looks like I have to put the textures of the mug, and since its a particular mug with some strange paintings I dont think I can do it..?);

 

- Tiny objects (I was trying to scan a proximity sensor (which also has some refflexive parts) and it went very poorly).

 

I even tried with 1 layer of tape to remove reflectiveness but the problem remained. So far things only went well with big, diffuse and unique objects (my wallet being an exception, which ended up perflect fine even though its a very basic wallet).

 

In case you're asking yourself why I'm picking so many different/random objects, I was trying to have a perception of the detection limits of Vuforia to check if it's a possible solution for my use case.

 

Thank you so much for reading and taking your time to help me out, I really appreciate it.

Object Detection on Simpler and/or Smaller Objects

October 26, 2018 - 11:04am #1

Hello,

The Object Target feature utilizes SLAM, which as you rightly pointed out will require surface features for performant detection and tracking.

Although I'm not hopeful that the object's you described are well suited for the feature, here are some tips that may make other objects more successful.

Thanks,

Vuforia Engine Support

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:

  1. 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.
  2. No direct lighting. We use light boxes and/or diffusers to eliminate direct lighting upon the object and minimize any spectral reflections.
  3. 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.
  4. 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.

Log in or register to post comments