IP Library › Granted Patent US 11,482,015
Granted Patent B2
US 11,482,015 · App. 16/536,439 · Granted Oct 25, 2022

Method for recognizing parking space for vehicle and parking assistance system using the method

Inventors: Pi-Hau Shih (Taipei, TW); Wei Jing Wong (Hsinchu, TW); Chen-Wei Hung (Hsinchu, TW)
Assignee: oToBrite Electronics Inc.
G06V20/586B60W30/06B62D15/027G06V20/58G08G1/143G08G1/168B60W2420/42
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 11,482,015
App. No.
16/536,439
Filed
Aug 9, 2019
Granted
Oct 25, 2022
Kind
B2
Art Unit
2668
USPC
382/104
Abstract

A method for recognizing a parking space for a vehicle and a parking assistance system are disclosed. An obstacle is identified from successive image frames captured when the vehicle is moving and a first boundary for the obstacle is generated by a Convolutional Neural Network (CNN) algorithm based on a position of the obstacle shown in each of the successive image frames. Distances between the moving vehicle and the obstacle are detected by ultrasonic sensors. A second boundary for the obstacle is generated by a distance modification module based on the distances between the vehicle and the obstacle. A periphery of the obstacle is defined by a periphery definition module. In view of the periphery of the obstacle, a parking space is thus recognized by a parking space recognition module. The parking process can be changed to a self-drive mode, and remotely controlled by a mobile device.

Claims (123)

1. A method for recognizing a parking space for a vehicle, comprising the steps of:

capturing successive image frames containing an obstacle while the vehicle is moving;

converting the successive image frames containing the obstacle into a birds-eye view image;

identifying the obstacle from the birds-eye view image and generating obstacle edge points of the obstacle by a Convolutional Neural Network (CNN) algorithm based on a position of the obstacle shown in each of the successive image frames;

generating a first boundary for the obstacle by merging and denoising the obstacle edge points generated by the CNN algorithm;

detecting a plurality of distances between the moving vehicle and the obstacle by at least an ultrasonic sensor;

generating a second boundary for the obstacle based on the plurality of distances between the moving vehicle and the obstacle detected by the ultrasonic sensor(s);

defining a periphery of the obstacle by refining y-coordinate of each point of the first boundary P fs (x fs , y fs ) based on the coordinates P sl (x sl , y sl ) and P sr (x sr , y sr ) of two adjacent corresponding points P sl and P sr of the second boundary according to the following equation:

y

fs

′

=

(

1

-

x

fs

-

x

sl

x

sr

-

x

sl

)

×

y

sl

+

(

x

f

⁢

s

-

x

sl

x

s

⁢

r

-

x

sl

)

×

y

sr

;

and

recognizing a parking space with the aid of the periphery of the obstacle.

2. A method for recognizing a parking space for a vehicle according to claim 1 , wherein the obstacle is an adjacent vehicle.

3. A method for recognizing a parking space for a vehicle according to claim 1 , further comprising a step of:

generating a parking track for the vehicle.

4. A method for recognizing a parking space for a vehicle according to claim 3 , further comprising a step of:

steering the vehicle to the parking space with reference to the parking track.

5. A method for recognizing a parking space for a vehicle according to claim 1 , wherein the parking space comprises an identifiable feature.

6. A method for recognizing a parking space for a vehicle according to claim 3 , wherein the parking track comprises an outline of the parking space and a path from a current position of the vehicle to the parking space.

7. A method for recognizing a parking space for a vehicle according to claim 4 , further comprising a step of:

steering the vehicle from the parking space to a designated location along the parking track.

8. A method for recognizing a parking space for a vehicle according to claim 2 , further comprising a step of:

displaying a top view of the moving vehicle and/or a top view of the adjacent vehicle.

9. A parking assistance system for a vehicle, comprising:

an image capture module for capturing successive image frames containing an obstacle when the vehicle is moving;

an image conversion module for converting each of the successive image frames containing the obstacle into a birds-eye view image;

an identification module for identifying the obstacle from the birds-eye view image and generating obstacle edge points of the obstacle by a Convolutional Neural Network (CNN) algorithm based on a position of the obstacle shown in each of the successive image frames and generating a first boundary for the obstacle by merging and denoising the obstacle edge points generated by the CNN algorithm;

at least an ultrasonic sensor for detecting a plurality of distances between the moving vehicle and the obstacle;

a distance modification module for generating a second boundary for the obstacle based on the plurality of distances between the moving vehicle and obstacle detected by the ultrasonic sensor(s);

a periphery definition module for defining a periphery of the obstacle by refining y-coordinate of each point of the first boundary P fs (x fs , y fs ) based on the coordinates P sl (x sl , y sl ) and P sr (x sr , y sr ) of two adjacent corresponding points P sl and P sr of the second boundary according to the following equation:

y

fs

′

=

(

1

-

x

f

⁢

s

-

x

sl

x

s

⁢

r

-

x

sl

)

×

y

sl

+

(

x

fs

-

x

sl

x

sr

-

x

sl

)

×

y

s

⁢

r

;

and

a parking space recognition module for recognizing a parking space with the aid of the periphery of the obstacle.

10. A parking assistance system according to claim 9 , wherein the obstacle is an adjacent vehicle.

11. A parking assistance system according to claim 9 , further comprising a parking track module for generating a parking track for the vehicle.

12. A parking assistance system according to claim 11 , further comprising a parking control device for steering the vehicle to the parking space with reference to the parking track.

13. A parking assistance system according to claim 9 , wherein the parking space comprises an identifiable feature.

14. A parking assistance system according to claim 11 , wherein the parking track comprises an outline of the parking space and a path from a current position of the vehicle to the parking space.

15. A parking assistance system according to claim 12 , wherein the parking control device is used for steering the vehicle from the parking space to a designated location along the parking track.

16. A parking assistance system according to claim 10 , further comprising a display for displaying a top view of the moving vehicle and/or a top view of the adjacent vehicle.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 9, 2019
From: SHIH, PI-HAU; WONG, WEI JING; HUNG, CHEN-WEI
To: OTOBRITE ELECTRONICS INC.
Reel/Frame 050009/0433 →
Continuity (1)
Related Publication 20210042540A1 · Feb 11, 2021
Cited By (2)
US 12,210,106 US 12,479,467