Systems and methods for mapping based on multi-journey data

Patent metadata

Field	Value
Publication number	US-12573208-B2
Application number	US-202318460306-A
Country	US
Kind code	B2
Filing date	Sep 1, 2023
Priority date	Jan 4, 2017
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

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.

First claim

What is claimed is:

1 . A vehicle, comprising:
at least one memory; and at least one processor coupled to the at least one memory and configured to:
receive a first plurality of tiles comprising first map data, wherein the first plurality of tiles is based on first image data received from a first vehicle;
receive a second plurality of tiles comprising an update to the first map data, wherein the second plurality of tiles is based on second image data received from a second vehicle and is associated with a similarity metric corresponding to the first map data of the first plurality of tiles and the second plurality of tiles;
store the received first plurality of tiles and the received second plurality of tiles; and
localize the vehicle based on the first plurality of tiles and the second plurality of tiles.

2 . The vehicle of claim 1 , wherein the first image data and the second image data represent an object.

3 . The vehicle of claim 2 , wherein the first 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.

4 . The vehicle of claim 3 , wherein the object cluster is based on feature points of the object represented in the first image data and feature points of the object represented in the second image data.

5 . The vehicle of claim 3 , wherein the first map data is based on a bundle adjustment that is based on the object cluster.

6 . The vehicle of claim 3 , wherein the at least one processor is configured to:
receive additional image data from a camera coupled to the vehicle; and localize the vehicle further based on the received additional image data.

7 . The vehicle of claim 6 , wherein the received additional 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.

8 . The vehicle of claim 2 , wherein the object is a lane marker or a sign.

9 . The vehicle of claim 2 , wherein the similarity metric is associated with the object represented in the first image data and the object represented in the second image data.

10 . The vehicle of claim 9 , wherein the similarity metric is based on a type of the object.

11 . The vehicle of claim 1 , wherein the at least one processor is configured to obtain local semantic information based on the localization, the first plurality of tiles, and the second plurality of tiles.

12 . The vehicle of claim 1 , wherein the first image data and the second image data include feature points.

13 . The vehicle of claim 1 , wherein the first image data and the second image data include camera pose information.

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 first plurality of tiles and the second plurality of tiles using the radio frequency signals.

16 . A method localizing a vehicle, comprising:
receiving a first plurality of tiles comprising first map data, wherein the first plurality of tiles is based on first image data received from a first vehicle; receiving a second plurality of tiles comprising an update to the first map data, wherein the second plurality of tiles is based on second image data received from a second vehicle and is associated with a similarity metric corresponding to the first map data of the first plurality of tiles and the second plurality of tiles; storing the received first plurality of tiles and the received second plurality of tiles; and localizing the vehicle based on the first plurality of tiles and the second plurality of tiles.

17 . The method of claim 16 , wherein the first image data and the second image data represent an object.

18 . The method of claim 17 , wherein the first 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.

19 . The method of claim 18 , wherein the object cluster is based on feature points of the object represented in the first image data and feature points of the object represented in the second image data.

20 . The method of claim 18 , wherein the first map data is based on a bundle adjustment that is based on the object cluster.

21 . The method of claim 18 , further comprising:
receiving additional image data from a camera coupled to the vehicle; and localizing the vehicle further based on the received additional image data.

22 . The method of claim 21 , wherein the received additional image data from the camera comprises a third plurality of tiles, the method further comprising transmitting the third plurality of tiles.

23 . The method of claim 17 , wherein the object is a lane marker or a sign.

24 . The method of claim 17 , wherein the similarity metric is associated with the object represented in the first image data and the object represented in the second image data.

25 . The method of claim 24 , wherein the similarity metric is based on a type of the object.

26 . The method of claim 16 , further comprising obtaining local semantic information based on the localization, the first plurality of tiles, and the second plurality of tiles.

27 . The method of claim 16 , wherein the first image data and the second image data include feature points.

28 . The method of claim 16 , wherein the first image data and the second image data include camera pose information.

29 . The method of claim 16 , wherein the vehicle comprises at least one antenna for receiving radio frequency signals.

30 . The method of claim 29 , wherein the first plurality of tiles and the second plurality of tiles are received using the radio frequency signals.

Assignees

• Qualcomm Inc

Inventors

• Dabeer Onkar Jayant
• Somasundaram Kiran
• Gowaikar Radhika Dilip
• Sukhavasi Ravi Teja

Classifications

• G06T17/05

  Geographic models · CPC title

• G01C21/30

  Map- or contour-matching · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06V10/7715

  Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods · CPC title

• G06V10/763

  Non-hierarchical techniques, e.g. based on statistics of modelling distributions · CPC title