Image Detection Technique Used in QCAR

Question

Can someone tell me what exactly and how exactly the image is recognized in Qualcomm QCAR https://developer.qualcomm.com/develop/mobile-technologies/augmented-reality . I would like to know which image detection algorithm is used.

Answer 1

QCAR is based on Studierstube ES , which is not publicly available. However, you might be interested in publications in an updated project with extended implementation, as some of them relate to Studierstube ES, the predecessor. Algorithms have been improved at the same time, but you can find out what they have developed.

I have not read newspapers, but they may be of interest to you:

http://www.icg.tugraz.at/publications/pdf/WAGNER_ISMAR08_AMT.pdf

http://www.icg.tugraz.at/publications/pdf/WAGNER_ISMAR08_NFT.pdf

http://www.icg.tugraz.at/Members/daniel/MultipleTargetTrackingPDF

http://www.icg.tugraz.at/Members/daniel/Publications/TVCG2010_RealTimeDetectionAndTrackingOnMobilePhones.pdf

Answer 2

Unfortunately, it seems that the QCAR on the Qualcomm website has virtually no documentation about the applied algorithms in the QCAR, except for “The QCAR SDK uses sophisticated algorithms to detect and track functions that are naturally found in the image itself”

However, there is some explanation about the different types of supported tracks that you might want to take a look at. I do not really like pattern recognition, but you can get some pointers to the basic algorithms from this.