What functions does the tango project use?
Does the tango project provide any visual features per frame (like ORB or SIFT / SURF)? or the whole point cloud is just 3D points extracted from the depth camera. If so, is it possible to know which algorithm they are using? Are they just corners?
I would like to drop a 3D point cloud along with related functions and wonder if this is possible in real time.
source to share
Unfortunately, they don't reveal what features they use. All you get is XYZ + Confidence. Here's a realtime cloud point callback, from the C API:
TangoErrorType TangoService_connectOnPointCloudAvailable(
void(*)(void *context, const TangoPointCloud *cloud) TangoService_onPointCloudAvailable,
...
);
Cm:
- https://developers.google.com/tango/apis/c/reference/group/depth
- https://developers.google.com/tango/apis/java/reference/TangoPointCloudData
- https://developers.google.com/tango/apis/unity/reference/class/tango/tango-unity-depth
TangoPointCloud
defined here:
- https://developers.google.com/tango/apis/c/reference/struct/tango-point-cloud#struct_tango_point_cloud
- https://developers.google.com/tango/apis/java/reference/TangoPointCloudData
- https://developers.google.com/tango/apis/unity/reference/class/tango/tango-point-cloud-data
As an aside, if you think the purpose of Tango is a portable API that sits on different different sensors and hardware platforms, then it makes sense that they won't reveal the details of the basic depth estimation method. This can change from one device to another.
By the way, they also keep the internals of their ADF (Area Description File) a secret.
source to share