Log in or register to post comments

Target size Spec

February 17, 2019 - 10:49pm #1

We would like to discuss one of the use cases we have and we are planning to use vuforia SDK for same, but we need to confirm a few things related to our use cases.

1) We have billboard hoarding advertisements which can vary from 4 * 4 sq ft to 150 * 150 sq ft size and we are planning to create of such sizes.

2) Now users can track such target from a distance of 4 ft to 100 ft

3) Does vuforia allow the users to track such targets? and how much min and max distance required for same?  

4) If not then what could be the alternate way to achieve such use cases?

Please advise on the above use cases

Target size Spec

February 18, 2019 - 3:26pm #2

Hello,

Vuforia has proven to be effective recognizing images of multiple sizes, including large, "billboard" sized targets.

You can estimate the minimum size that your target should have by dividing your camera-to-target distance by ~10. For instance, a 20 cm wide target would be detectable up to a distance of about 2 meters (20 cm x 10). Note, however, that this is just a rough indication and the actual working distance/size ratio can vary based on lighting conditions, camera focus, target rating, SDK version and device. Some of these points are covered in the following article: https://library.vuforia.com/articles/Solution/Optimizing-Target-Detection-and-Tracking-Stability

Another strategy that has been employed in the past is to use the Vuforia feature MultiTargets to divide large targets (i.e. billboards, building wall murals) into "sections" for easier detection.

https://library.vuforia.com/content/vuforia-library/en/articles/Training/Multi-Target-Guide.html

The target image would be divided into n sections by modifying the MultiTarget's dataset's configuration file: https://library.vuforia.com/articles/Solution/How-To-Modify-the-Dataset-Configuration-XML-File-Outside-the-Target-Manager#How-To-Modify-a-Multi-Target-Using-its-Config-XML-File. This allows for the user's camera to *not* have to see the entire image to detect it. This is especially useful if the device is close to a large target.

Good luck.

-Vuforia Engine Support

Log in or register to post comments