Arcona SLAM engine is a turnkey solution for precise placement of AR content and binding it to real geo locations with accuracy higher than GPS.
Arcona SLAM can be used as an add-on to the popular AR engines like ARKit and ARCore, but also provides its own AR tracking system for custom solutions.
Our system has two options for precise geo-localization:
1) correct transformation from the local device coordinate system to the world coordinate system (LWT) using only GPS and compass information;
2) LWT using our 3D maps with spatial anchors.
Our 3D maps are implemented as a set of independent spatial anchors; each anchor consists of visual and geometry elements. Such set of anchors is created from sampled data packages obtained by a mobile device with the standard sensor kit: camera, GPS, compass, accelerometer, gyroscope.
Map creation cost is scalable and depends on the anchor quality requirements; thus the map can be created on a powerful server, as well as on a mobile device, “in place”.
To solve localization tasks Arcona has a software set consists of the following components:
SLAM engine;cation to collect and transfer device sensor data;
SLAM engine;
LWT estimator;
spatial anchor creator;
perception unit to recognize the spatial anchors.
Comparison of Arcona with other AR/SLAM systems.
| Arcona | Snap | Niantic | Wikitude |
---|---|---|---|---|
own SLAM engine | ✅ | ✅ | ✅ | ✅ |
ArKit support | ✅ | ❌ | ✅ | ✅ |
ArCore support | ✅ | ✅ | ✅ | ✅ |
GPS/compass auto correction | ✅ | ❌ | ❌ | ❌ |
visual relocalization | ✅ | ✅ | ✅ | ✅ |
visual spatial anchor generation | ✅ | ✅ | ✅ | ✅ |
place sampling datasets gathering | ✅ | ✅ | ✅ | ✅ |
remote content placement | ✅ | ✅ | ✅ | ✅ |
low-light odometry | ❌ | ❌ | ❌ | ❌ |
low-light place recognition | ✅ | ❌ | ❌ | ❌ |
foggy air odometry | ❌ | ❌ | ❌ | ❌ |
foggy air place recognition | ✅ | ❌ | ❌ | ❌ |
weak devices support | ✅ | ❌ | ❌ | ✅ |
Comments