Multicamera system for autonamous driving vehicles

Patent metadata

Field	Value
Publication number	US-2020172014-A1
Application number	US-201816208483-A
Country	US
Kind code	A1
Filing date	Dec 3, 2018
Priority date	Dec 3, 2018
Publication date	Jun 4, 2020
Grant date	—

Abstract

Embodiments of the disclosure provide a camera system for a vehicle and a sensing method using such a camera system. The camera system includes a plurality of cameras each configured with a different camera setting. The cameras collectively keep a predetermined image space in focus. The predetermined image space includes at least one object. The camera system further includes a controller. The controller is configured to receive image data captured by the plurality of cameras of the predetermined image space, and determine depth information of the at least one object based on the image data.

First claim

1 . A camera system for a vehicle, comprising:
a plurality of cameras each configured with a different camera setting, collectively keeping a predetermined image space in focus, wherein the predetermined image space includes at least one object, wherein the predetermined image space is defined relative to the vehicle and wherein the plurality of cameras are located at a plurality of different positions on the vehicle; and a controller, configured to:
receive image data captured by the plurality of cameras of the predetermined image space; and
determine depth information of the at least one object based on the image data, wherein the depth information comprises a position of the at least one object relative to the vehicle.

2 . The system of claim 1 , wherein the vehicle is an autonomous driving vehicle, and wherein the controller is further configured to make an autonomous driving decision based on the image data.

3 . The system of claim 1 , wherein each camera is configured with a different focal length.

4 . The system of claim 3 , wherein the controller is configured to:
determine focused distances of the plurality of cameras, based on focal lengths of the cameras; identify at least one camera, among the plurality of cameras, in which an object of the at least one object is in focus; and determine the depth information of the object based on the focused distance of the identified camera.

5 . The system of claim 1 , wherein each camera is configured with a different angle of view.

6 . The system of claim 1 , wherein the plurality of cameras include two sets of cameras, each set of cameras at a different location of the vehicle.

7 . The system of claim 6 , wherein the two sets of cameras are configured with orthogonal polarization.

8 . The system of claim 1 , wherein the plurality of cameras include a first camera and a second camera, wherein the controller is further configured to correct artifacts in image data captured by the first camera using image data captured by the second camera.

9 . The system of claim 1 , wherein the plurality of cameras are configured to point to a same direction.

10 . A vehicle, comprising:
a body; at least one wheel; a plurality of cameras equipped on the body and configured with a different camera setting, collectively keeping a predetermined image space in focus, wherein the predetermined image space includes at least one object, wherein the predetermined image space is defined relative to the vehicle, and wherein the plurality of cameras are located at a plurality of different positions on the vehicle; and a controller, configured to:
receive image data captured by the plurality of cameras of the predetermined image space;
determine depth information of the at least one object based on the image data wherein the depth information comprises a position of the at least one object relative to the vehicle; and
control at least one function of the vehicle based on the depth information.

11 . The vehicle of claim 10 , wherein the vehicle is an autonomous driving vehicle, and wherein the controller is further configured to make an autonomous driving decision based on the image data.

12 . The vehicle of claim 10 , wherein each camera is configured with a different focal length.

13 . The vehicle of claim 12 , wherein the controller is configured to:
determine the focused distances of the plurality of cameras, based on focal lengths of the cameras; identify at least one camera, among the plurality of cameras, in which an object of the at least one object is in focus; and determine the depth information of the object based on the focused distance of the identified camera.

14 . The vehicle of claim 10 , wherein each camera is configured with a different angle of view.

15 . The vehicle of claim 10 , wherein the plurality of cameras include two sets of cameras, each set of cameras at a different location of the vehicle, wherein the two sets of cameras are configured with orthogonal polarization.

16 . A sensing method, comprising:
capturing image data of a predetermined image space including at least one object using a plurality of cameras each configured with a different camera setting, collectively keeping a predetermined image space in focus, wherein the predetermined image space is defined relative to a vehicle and wherein the plurality of cameras are located at a plurality of different positions on the vehicle; and determining, by at least one processor, depth information of the at least one object based on the image data, wherein the depth information comprises a position of the at least one object relative to the vehicle.

17 . The sensing method of claim 16 , wherein the vehicle comprises an autonomous driving vehicle on which the plurality of cameras are equipped, and the method further includes:
making an autonomous driving decision based on the image data.

18 . The sensing method of claim 16 , wherein each camera is configured with a different focal length, and wherein determining depth information further includes:
determining the focused distances of the plurality of cameras, based on focal lengths of the cameras; identifying at least one camera, among the plurality of cameras, in which an object of the at least one object is in focus; and determining the depth information of the object based on the focused distance of the identified camera.

19 . The sensing method of claim 16 , wherein the plurality of cameras include a first camera and a second camera, wherein the method further includes:
correcting artifacts in image data captured by the first camera using image data captured by the second camera

20 . The sensing method of claim 16 , wherein each camera is configured with a different angle of view.

Assignees

• Didi Res America Llc

Inventors

• Takhirov Zafar
• Hu Sen

Classifications

• B60R2300/107

  using stereoscopic cameras · CPC title

• B60R1/002 Primary

  specially adapted for covering the peripheral part of the vehicle, e.g. for viewing tyres, bumpers or the like (integrated in the windows B60R1/001; combined with rear-view mirrors B60R1/08) · CPC title

• B60R2300/105

  using multiple cameras · CPC title

• B60R2300/8093

  for obstacle warning · CPC title

• B60R2300/303

  using joined images, e.g. multiple camera images · CPC title