IP Library Granted Patent US 11,217,091
Granted Patent B2
US 11,217,091 · App. 16/523,742 · Granted Jan 4, 2022

Smart roadside unit and method for processing information by smart roadside unit

Inventors: Lei Fang (Beijing, CN); Haisong Wang (Beijing, CN); Xing Hu (Beijing, CN); Sheng Tao (Beijing, CN)
Assignee: Apollo Intelligent Driving Technology (Beijing) Co., Ltd.
G08G1/04G06K9/00785H04N5/22521H04N5/247G06K2209/15G06K2209/23
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,217,091
App. No.
16/523,742
Granted
Jan 4, 2022
Kind
B2
Abstract

Provided is a smart roadside unit, including: a high-bright camera assembly configured to capture a high-bright image; a low-bright camera assembly configured to capture a low-bright image, in which the high-bright camera assembly and the low-bright camera assembly have a substantially same shooting view; and a controller configured to extract vehicle information from the high-bright image and the low-bright image.

Claims (47)

1. A smart roadside unit, mounted on a roadway, comprising:

a high-bright camera assembly configured to capture a high-bright image;

a low-bright camera assembly configured to capture a low-bright image, wherein the high-bright image and the low-image are acquired at the high-bright camera assembly and the low-bright camera assembly have a substantially same shooting view and the high-bright camera assembly has a lower ISO sensitivity than the low-bright camera assembly; and

a controller configured to extract vehicle information from the high-bright image and the low-bright image.

2. The smart roadside unit according to claim 1 , wherein the high-bright camera assembly and the low-bright camera assembly have a substantially same shooting angle and a substantially same shooting area.

3. The smart roadside unit according to claim 1 , wherein the controller is further configured to:

select a first region which is clear under a high-bright environment from the high-bright image,

select a second region which is clear under a low-bright environment from the low-bright image,

combine the first region and the second region to generate a target image, and

extract the vehicle information from the target image.

4. The smart roadside unit according to claim 1 , further comprising:

a first shielding layer covering at least part of the high-bright camera assembly and

a second shielding layer covering at least part of the low-bright camera assembly.

5. The smart roadside unit according to claim 4 , wherein the first shielding layer does not cover camera lenses and heat dissipation components of the high-bright camera assembly; and

the second shielding layer does not cover camera lenses and heat dissipation components of the low-bright camera assembly.

6. The smart roadside unit according to claim 1 , further comprising:

a first radar, and

a second radar, wherein a detection distance of the first radar is greater than a detection distance of the second radar.

7. The smart roadside unit according to claim 6 , wherein the first radar is disposed relatively higher than the second radar in a vertical direction.

8. The smart roadside unit according to claim 6 , wherein the first radar and the second radar are both laser radars.

9. The smart roadside unit according to claim 1 , further comprising:

an antenna, wherein a distance between the antenna and the camera assembly is greater than a preset distance.

10. The smart roadside unit according to claim 1 , further comprising:

a traffic light controlled by the controller according to extracted vehicle information.

11. A method for processing information by a smart roadside unit mounted on a roadway, comprising:

capturing a high-bright image by a high-bright camera assembly and capturing a low-bright image by a low-bright camera assembly, wherein the high-bright image and the low-bright image are acquired at the same time, the high-bright camera assembly and the low-bright camera assembly have a substantially same shooting view and the high-bright camera assembly has a lower ISO sensitivity than the low-bright camera assembly;

extracting vehicle information from the high-bright image and the low-bright image.

12. The method according to claim 11 , wherein extracting vehicle information from the high-bright image and the low-bright image comprises:

selecting a first region which is clear under a high-bright environment from the high-bright image,

selecting a second region which is clear under a low-bright environment from the low-bright image,

combining the image of the high-bright region and the image of the low-bright region to generate a target image, and

extracting the vehicle information from the target image.

13. The method according to claim 11 , wherein a first shielding layer is provided to cover at least part of the high-bright camera assembly; and

a second shielding layer is provided to cover at least part of the low-bright camera assembly.

14. The method according to claim 13 , wherein the first shielding layer does not cover camera lenses and heat dissipation components of the high-bright camera assembly; and

the second shielding layer does not cover camera lenses and heat dissipation components of the low-bright camera assembly.

15. The method according to claim 11 , further comprising:

acquiring first obstacle information by a first radar, and

acquiring second obstacle information by a second radar, wherein a detection distance of the first radar is greater than a detection distance of the second radar.

16. The method according to claim 15 , further comprising:

sending the obstacle information and captured images to a server or a vehicle via an antenna.

17. The method according to claim 15 , wherein the first radar and the second radar are both laser radars.

18. The method according to claim 11 , further comprising:

controlling a traffic light according to extracted vehicle information.

19. A non-temporary computer-readable storage medium having stored therein computer programs that, when executed by a processor, cause the processor to perform a method for processing information acquired by a smart roadside unit mounted over on a roadway, the method comprising:

capturing a high-bright image by a high-bright camera assembly and capturing a low-bright image by a low-bright camera assembly, wherein the high-bright image and the low-bright image are acquired at the same time, the high-bright camera assembly and the low-bright camera assembly have a substantially same shooting view and the high-bright camera assembly has a lower ISO sensitivity than the low-bright camera assembly;

extracting vehicle information from the high-bright image and the low-bright image.

Assignments (3)
CORRECTIVE ASSIGNMENT TO CORRECT THE APPLICANT NAME PREVIOUSLY RECORDED AT REEL: 057933 FRAME: 0812. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Dec 28, 2021
From: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
To: APOLLO INTELLIGENT DRIVING TECHNOLOGY (BEIJING) CO., LTD.
Reel/Frame 058594/0836 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 13, 2021
From: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
To: APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO., LTD.
Reel/Frame 057933/0812 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 26, 2019
From: FANG, LEI; WANG, HAISONG; HU, XING; TAO, SHENG
To: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
Reel/Frame 049876/0745 →
Priority Claims (1)
CN 201811012972.7 · Aug 31, 2018 · national
Continuity (1)
Related Publication 20200074855A1 · Mar 5, 2020