SYSTEMS AND METHODS FOR MAPPING BASED ON MULTI-JOURNEY DATA
A method performed by an apparatus is described. The method includes receiving map data that is based on first image data, second image data, and a similarity metric. The first image data can be received from a first vehicle and represent an object. The second image data can be received from a second vehicle and represent the object. The similarity metric can be associated with the object represented in the first image data and the object represented in the second image data. The method can also include storing, by a vehicle, the received map data and localizing the vehicle based on the stored map data.
1 . A vehicle, comprising:
at least one memory; and
at least one processor coupled to the at least one memory and configured to:
obtain sensor data;
extract first feature data from the sensor data;
transmit the first feature data to a server;
receive, from the server, map data associated with the first feature data and second feature data from an additional vehicle, wherein the map data is based on a similarity metric corresponding to the first feature data and the second feature data;
store the received map data; and
localize the vehicle based on the map data.
2 . The vehicle of claim 1 , wherein the map data includes a plurality of tiles.
3 . The vehicle of claim 1 , wherein the sensor data includes first image data representing an object, and wherein the second feature data is based on second image data representing an object.
4 . The vehicle of claim 3 , wherein the map data is based on an object cluster associated with the object represented in the first image data and the object represented in the second image data.
5 . The vehicle of claim 4 , wherein the first feature data is associated with first feature points of the object represented in the first image data, wherein second feature data extracted from the second image data is associated with second feature points of the object represented in the second image data, and wherein the object cluster is based on the first feature points of the object represented in the first image data and the second feature points of the object represented in the second image data.
6 . The vehicle of claim 4 , wherein the map data is based on a bundle adjustment that is based on the object cluster.
7 . The vehicle of claim 4 , wherein the sensor data includes first image data, and wherein the at least one processor is configured to:
receive the first image data from a camera coupled to the vehicle; and
localize the vehicle further based on the received first image data.
8 . The vehicle of claim 7 , wherein the received first image data from the camera comprises a third plurality of tiles, and wherein the at least one processor is configured to transmit the third plurality of tiles.
9 . The vehicle of claim 3 , wherein the object is a lane marker or a sign.
10 . The vehicle of claim 3 , wherein the similarity metric is associated with the object represented in the first image data and the object represented in the second image data.
11 . The vehicle of claim 10 , wherein the similarity metric is based on a type of the object.
12 . The vehicle of claim 3 , wherein the first image data and the second image data include camera pose information.
13 . The vehicle of claim 1 , wherein the at least one processor is configured to obtain local semantic information based on the localization and the map data.
14 . The vehicle of claim 1 , further comprising at least one antenna for receiving radio frequency signals.
15 . The vehicle of claim 14 , wherein the at least one antenna is configured to receive the map data using the radio frequency signals.
16 . A method localizing a vehicle, comprising:
obtaining sensor data;
extracting first feature data from the sensor data;
transmitting the first feature data to a server;
receiving, from the server, map data associated with the first feature data and second feature data from an additional vehicle, wherein the map data is based on a similarity metric corresponding to the first feature data and the second feature data;
storing the received map data; and
localizing the vehicle based on the map data.
17 . The method of claim 16 , wherein the map data includes a plurality of tiles.
18 . The method of claim 16 , wherein the sensor data includes first image data representing an object, and wherein the second feature data is based on second image data representing an object.
19 . The method of claim 18 , wherein the map data is based on an object cluster associated with the object represented in the first image data and the object represented in the second image data.
20 . The method of claim 19 , wherein the first feature data is associated with first feature points of the object represented in the first image data, wherein second feature data extracted from the second image data is associated with second feature points of the object represented in the second image data, and wherein the object cluster is based on the first feature points of the object represented in the first image data and the second feature points of the object represented in the second image data.