Method and device for determining an environment map by a server using motion and orientation data
Method for determining an environment map comprising, server-side receiving of motion data of a mobile device, server-side receiving of orientation data of a camera of the mobile device and server-side receiving of the respective image of the camera associated with the received motion data and orientation data, server-side evaluation of the received image together with the motion data and the orientation data for creating a server-side point cloud, the server-side point cloud forming at least in parts the environment map.
1. A method for determining an environment map comprising:
server-side receiving of motion data from a mobile device;
server-side receiving of orientation data of a camera of the mobile device;
server-side receiving of an image of the camera associated with the motion data and the orientation data; and
server-side evaluating the image together with the motion data and the orientation data to create a server-side point cloud, wherein the server-side point cloud forms the environment map at least in parts.
2. The method according to claim 1 , wherein
a mobile station-side point cloud created by the mobile device is received on the server-side, and
the server-side point cloud is combined with the mobile station-side point cloud to form a new server-side point cloud.
3. The method according to claim 2 , wherein
during the combination of the mobile station-side point cloud with the server-side point cloud:
points of the server-side point cloud are at least partially supplemented by points of the mobile station-side point cloud, and/or
point coordinates of the points of the server-side point cloud are at least partially converted with aid of point coordinates of the points of the mobile-station-side point cloud and/or vice versa.
4. The method according to claim 1 , wherein
point coordinates represent a point cloud, points of the point cloud correspond respectively to a point coordinate.
5. The method according to claim 4 , wherein
the point coordinates are represented by vectors.
6. The method according to claim 2 , wherein
point coordinates of points of the mobile station-side point cloud are changed with aid of the motion data and/or the orientation data evaluated on the server-side, in particular in that a drift of the point coordinates of the points on the mobile station-side point cloud is corrected.
7. The method according to claim 1 , wherein
the orientation data is corrected on the server-side with aid of the motion data.
8. The method according to claim 1 , wherein
a feature recognition and/or a feature description is carried out on the server-side in the image, in particular by means of multi-scale oriented patches (MOPS) or scale-invariant feature transform (SIFT).
9. The method according to claim 1 , wherein
features are learned on the server-side during feature recognition and/or a feature description, in particular in that deep learning is performed.
10. The method according to claim 1 , wherein
a bundle adjustment is performed on the server-side in the image.
11. The method according to claim 2 , wherein
an outlier removal is carried out on the server-side in the mobile station-side point cloud, in particular by means of statistical evaluation.
12. The method according to claim 2 , wherein
the mobile station-side point cloud is generated by means of visual, motion-related odometry.
13. The method according to claim 2 , wherein
a loop closure is determined with aid of the server-side point cloud, and in that a drift of points of the mobile-station-side point cloud is corrected on a basis of the loop closure, in particular a linear adjustment of the drift being carried out.
14. The method according to claim 1 , wherein
depending on the server-side evaluation of the image, setting data for a mobile-station-side camera are determined and transmitted to the mobile device.
15. The method according to claim 2 , wherein
the new server-side point cloud is transmitted to the mobile device.
16. The method according to claim 1 , wherein
the server-side point cloud is enriched with anchors.
17. The method according to claim 1 , wherein
the server-side point cloud is received by the mobile device, and in that an augmented reality application is initialized in the mobile device using the server-side point cloud.
18. The method according to claim 1 , wherein
mobile station point clouds are received from a plurality of mobile devices at the server-side, in that the mobile station point clouds are used to adapt the server-side point cloud.
19. The method according to claim 1 , wherein
at least two instances are determined for the server-side point cloud, wherein in each instance at least one feature is learned by feature recognition and/or a feature description on the server-side and the respective instances together with features are transmitted to a mobile device.
20. A server arranged for determining an environment map comprising:
a receiving device arranged for receiving motion data of a mobile device, orientation data of a camera of the mobile device and an image of the camera assigned to the motion data and the orientation data; and
a computing device arranged for evaluating the image together with the motion data and the orientation data to generate a server-side point cloud, the server-side point cloud forming the environment map at least in parts.