Search code examples
augmented-realityarcoreazure-spatial-anchors

In which case the SLAM technique is used?


I am doing a study related to the field of augmented reality, and especially related to Google's ARCore technology. I would like to know if the SLAM method is required for model-based tracking. It seems obvious to me that it is not used in this case, but I could not find any article to confirm this. My second question is similar to the first one and is related to the Azure Spatial Anchors technology. This technology has the ability to recognize a scene that has been visualized during a previous session. In a way, the Azure Spatial Anchors technology reminds me a little bit of the model based tracking technology, knowing that the model based tracking has the ability to recognize a 3D object that has been previously recorded. So, in the same way I was wondering if the use of the Azure Spatial Anchors technology requires the use of the slam method ?


Solution

  • Have a look at Frequently asked questions about Azure Spatial Anchors

    Azure Spatial Anchors depends on mixed reality / augmented reality trackers. These trackers perceive the environment with cameras and track the device in 6-degrees-of-freedom (6DoF) as it moves through the space.

    Given a 6DoF tracker as a building block, Azure Spatial Anchors allows you to designate certain points of interest in your real environment as "anchor" points. You might, for example, use an anchor to render content at a specific place in the real-world.

    When you create an anchor, the client SDK captures environment information around that point and transmits it to the service. If another device looks for the anchor in that same space, similar data transmits to the service. That data is matched against the environment data previously stored. The position of the anchor relative to the device is then sent back for use in the application.

    ...

    For each point in the sparse point cloud, we transmit and store a hash of the visual characteristics of that point. The hash is derived from, but does not contain, any pixel data.

    There is disclosure in Microsoft Research Blog that the same type of visual simultaneous localization and mapping (SLAM) algorithms are being used with Azure Spatial Anchors: Azure Spatial Anchors: How it works

    For further details on the algorithm under NDA you can Open a tech support ticket.