Dear all,
I am quite confused about these two terms.
May I know if VISLAM is the same as VIO?
Does VISLAM uses front Hi res camera for localization or just using downward facing camera?
What is the algorithm behind both VISLAM and VIO for localization?
Thanks!
Sam
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
Hi Sam,
Sorry for the confusion; these terms are often used interchangeably. VISLAM, which stands for Visual-Inertial Simultaneous Localization and Mapping, is the name of an algorithm provided by the Qualcomm Machine Vision SDK. VIO, which stands for Visual-Inertial Odometry, is a more general term often applied to the family of algorithms that fuse vision data with inertial measurements to provide a six degree-of-freedom pose estimate. In the context of Snapdragon Navigator, both names refer to the same underlying algorithm.
Snapdragon Navigator only supports running VISLAM on the downward-facing global shutter camera at this time. However, the VISLAM API supports rolling shutter cameras as well, so the algorithm itself could be used with the forward-facing high resolution rolling shutter camera.
Hi jackdoc,
Thanks for your clarification.
May I know where I can find more reading on VISLAM? Like how it computes the 6DOF pose? This is really interesting!
Sam
You can't. The algorithms are a well-kept secret. The only thing you can do is display the features it is tracking and take a guess.