Apparatus and method for providing guidance information using crosswalk recognition result

• US 10,551,198 B2
• Filed: 11/17/2017
• Issued: 02/04/2020
• Est. Priority Date: 05/22/2015
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Kia Corp.
• Original Assignee: Thinkware Corporation
• Inventors: Lee, Han Woo
• Primary Examiner(s): Beaulieu, Yonel
• Application Number:
  US15/816,866
• Publication Number:
  US 20180073877A1
• Time in Patent Office: 809 Days
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01C 21/3647 Guidance involving output of stored or live camera images or video streams
• CPC Class Codes: G01S 19/13 Receivers
• CPC Class Codes: G01S 19/14 specially adapted for specific applications
• CPC Class Codes: G01S 19/485 whereby the further system is an optical system or imaging system
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

An apparatus of providing guidance information provides guidance information about the result of recognizing a crosswalk around a vehicle as information for inducing safe driving. The guidance information about a crosswalk is differently provided in accordance with a surrounding situation concerned with forward traveling of the vehicle.

Claims

1. A method of providing guidance information, the method being implemented by a computer, the method comprising:

acquiring a forward image of a user vehicle by a camera;

setting a portion of the forward image as a region of interest (ROI) to detect at least one of a lane, a pedestrian, a traffic light, a crosswalk, and a vehicle, wherein setting the portion of the forward image as the ROI comprises detecting the traffic light;

providing guidance information associated with said at least one of the lane, the pedestrian, the traffic light, the crosswalk, and the vehicle detected based on the set ROI; and

determining whether a sign of the detected traffic light is red, green, or yellow based on a sensed wavelength of light from the traffic light, or determining whether a sign of the detected traffic light is flickering,

wherein providing the guidance information comprises providing the guidance information including information on the determined sign of the detected traffic light.

2. The method of claim 1, wherein when the set ROI is a ROI for detecting the lane, among a plurality of straight line candidates detected from the forward image, a straight line candidate which has a constant line width with respect to the traveling direction of the user vehicle is detected as the lane.

3. The method of claim 1, wherein when the set ROI is a ROI for detecting the pedestrian, the ROI is set in accordance with a pedestrian recognizable distance in which the pedestrian is recognizable.

4. The method of claim 3, wherein the pedestrian is detected within the pedestrian recognizable distance by using a machine-learning result trained with pedestrians.

5. The method of claim 4, wherein when the pedestrian is detected, the guidance information indicates an existence of the pedestrian in a forward direction of the user vehicle.

6. The method of claim 4, wherein the method further comprises:

generating, when the pedestrian is detected, a signal to control the user vehicle to be decelerated or be braked.

7. The method of claim 1, wherein when the set ROI is a ROI for detecting a vehicle in a forward direction of the user vehicle, the vehicle in the forward direction is detected in the ROI by using a machine-learning result trained with vehicles.

8. The method of claim 7, wherein the vehicle in the forward direction is detected based on a spatial ratio feature that a width of the vehicle in the forward direction from side to side is reduced as a distance between the vehicle in the forward direction and the user vehicle is increased, and the width is widened as the distance is reduced.

9. An apparatus of providing guidance information, the apparatus comprising:

a memory in which at least one program is loaded; and

at least one processor, wherein, in accordance with the program, the at least one processor performs;

acquiring a forward image of a user vehicle by a camera;

setting a portion of the forward image as a region of interest (ROI) to detect at least one of a lane, a pedestrian, a traffic light, a crosswalk, and a vehicle wherein setting the portion of the forward image as the ROI comprises detecting the traffic light; and

providing guidance information associated with said at least one of the lane, the pedestrian, the traffic light, the crosswalk, and the vehicle detected based on the set ROI; and

determining whether a sign of the detected traffic light is red, green, or yellow based on a sensed wavelength of light from the traffic light, or determining whether a sign of the detected traffic light is flickering,

wherein providing the guidance information comprises providing the guidance information including information on the determined sign of the detected traffic light.

10. The apparatus of claim 9, wherein when the set ROI is a ROI for detecting the lane, among a plurality of straight line candidates detected from the forward image, a straight line candidate which has a constant line width with respect to the traveling direction of the user vehicle is detected as the lane.

11. The apparatus of claim 9, wherein when the set ROI is a ROI for detecting the pedestrian, the ROI is set in accordance with a pedestrian recognizable distance in which the pedestrian is recognizable.

12. The apparatus of claim 11, wherein the pedestrian is detected within the pedestrian recognizable distance by using a machine-learning result trained with pedestrians.

13. The apparatus of claim 12, wherein when the pedestrian is detected, the guidance information indicates an existence of the pedestrian in a forward direction of the user vehicle.

14. The apparatus of claim 12, wherein the at least one processor further performs:

generating, when the pedestrian is detected, a signal to control the user vehicle to be decelerated or be braked.

15. The apparatus of claim 9, wherein when the set ROI is a ROI for detecting a vehicle in a forward direction of the user vehicle, the vehicle in the forward direction is detected in the ROI by using a machine-learning result trained with vehicles.

16. The apparatus of claim 15, wherein the vehicle in the forward direction is detected based on a spatial ratio feature that a width of the vehicle in the forward direction from side to side is reduced as a distance between the vehicle in the forward direction and the user vehicle is increased, and the width is widened as the distance is reduced.