Introducing Project Tango Area Learning - Google I/O 2016
Why Stack Overflow recommends it
Stack Overflow users link it as the main reference for Project Tango's drift correction and area learning features, especially when asking how to enable or visualize them in the SDKs.
Recommended by 0 people across 0 different months, 2016 to 2017.
What it is
A Google I/O 2016 talk introducing Area Learning for Project Tango, Google's mobile motion-tracking and depth-sensing platform. It covers how a device can remember a space to anchor virtual objects, support multiplayer AR, pause and resume experiences, and correct motion tracking drift, plus best practices for developers.
What people said
Cites Konsti · 2016-06 · Stack Overflow · on “Drift Correction update of Project Tango after Google IO”
I am looking for the drift correction update for the project tango APIs after the presentation on the Google IO 2016. You can find the video at this link [this video] . The drift correction update is presented about 22:00 min. I hoped this function would be available after the big Okul update on June 9th, but I can't find it in any API. Does anyone one when this function will be available? The screenshot below shows what I'm looking for. The KEY_BOOLEAN_ENABLE_DRIFT_CORRECTION isn't available in any of the APIs. [LINK] I'm working with Java and Android Studio, but I would also be happy if this new function will be available in C or Unity API.
Cites Pado · 2016-07 · Stack Overflow · on “Generate and export point cloud from Project Tango”
Yes, you have to use TangoPoseData . I guess you are using TangoXyzIjData correctly; but the data you get this way is relative to where the device is and how the device is tilted when you take the shot. Here's how i solved this: I started from java_point_to_point_example [LINK] . In this example they get the coords of 2 different points with 2 different coordinate system and then write those coordinates wrt the base Coordinate frame pair. First of all you have to setup your exstrinsics, so you'll be able to perform all the transformations you'll need. To do that I call mExstrinsics = setupExtrinsics(mTango) function at the end of my setTangoListener() function. Here's the code (that you can
Cites m4pcy5t0 · 2016-10 · Stack Overflow · on “Visual feedback for area learning and motion tracking in Unity”
I'm getting pretty bad results with Area Learning, the localization takes very long and I have no idea what's happening. Did I map the area enough? Is there enough landmarks? Is the ADF alright? No clue. Is there any way to provide a visual feedback while doing the actual motion tracking and area learning? I keep seeing it in Google videos but didn't find any way of doing it in the Unity SDK. I would like something like this in my video overlay: [this video] Btw my results in Unity are FAR worse than this demo, sometimes it takes minutes for the device to localize and only at a certain spot in the room, the next minute the very same spot doesn't work again. Quite frustrating. No idea what app the
Cites 金圣韬 · 2017-08 · Stack Overflow · on “How to turn on area-learning during motion-tracking?”
I'm new of tango development. And I have applyed for the certificate of tango's vps(Visual Positioning Service) ,but there is no response unfortunately. For now, How I can run motion-tracking without drifting? I mean I don't like to take my tango device walking around the room to learn the area and generate adf files, or loading any descriptions previous learned. Is there any approach to learn and save scene feature points during tracking ,just as the slam does? I have watched the talk of google I/O 2016, and found the point: [this video] screen capture [LINK] Dose it work?