System and method of detecting preceding vehicle by using sensor

Patent metadata

Field	Value
Publication number	US-9829570-B2
Application number	US-201514613859-A
Country	US
Kind code	B2
Filing date	Feb 4, 2015
Priority date	Mar 5, 2014
Publication date	Nov 28, 2017
Grant date	Nov 28, 2017

Abstract

The present invention provides a system and a method of detecting a preceding vehicle. The system for detecting a preceding vehicle includes: an image sensor configured to generate image information containing information on reception intensity of light reflected from a preceding vehicle; a pixel detection unit configured to detect pixel areas corresponding to light reflected from rear reflectors of the preceding vehicle from the generated image information; and an Autonomous Emergency Braking (AEB) operation point controller configured to group adjacent pixel areas among the detected pixel areas, and classify the kind of vehicle of the preceding vehicle by using at least one element of information between information on the number of grouped pixel areas and information on an interval.

First claim

What is claimed is:

1. An apparatus to detect a preceding vehicle, comprising:
an image sensor configured to generate image information containing information on reception intensity of light reflected from a preceding vehicle;
a pixel detection unit configured to detect pixel areas corresponding to light reflected from rear reflectors of the preceding vehicle from the generated image information; and
an autonomous emergency braking (AEB) operation point controller configured to group adjacent pixel areas among the detected pixel areas, and to classify a kind of vehicle of the preceding vehicle by using at least one element of information between information on a number of the grouped pixel areas and information on an interval.

2. The apparatus of claim 1 , wherein the AEB operation point controller comprises:
a classifier configured to classify the kind of vehicle of the preceding vehicle, and
an operation point determination unit configured to determine an operation point of an AEB system of a host vehicle according to the classified kind of vehicle.

3. The apparatus of claim 1 , wherein the AEB operation point controller is further configured to classify the preceding vehicle as a two-wheel vehicle, in response to the number of the grouped pixel areas being one, and to classify the preceding vehicle as a four-wheel vehicle, in response to the number of the grouped pixel areas being two and an interval between the grouped pixel areas falling within a rear reflector reference interval range.

4. The apparatus of claim 1 , wherein the AEB operation point controller is further configured to classify a group comprising a second largest interval among the intervals between the grouped pixel areas as a group of the rear reflectors of the four-wheel vehicle, in response to the number of the grouped pixel areas being three.

5. The apparatus of claim 1 , wherein the AEB operation point controller is further configured to classify the preceding vehicle as any one of a small-size vehicle, a midsize vehicle, and a full-size vehicle, according to the information on the interval between the grouped pixel areas.

6. The apparatus of claim 1 , wherein the AEB operation point controller is further configured to calculate a difference in a grade value between the preceding vehicle and the host vehicle with reference to a table in which grades of the kind of vehicle are numerically expressed, and to determine an operation point of the AEB system of the host vehicle according to a result of the calculation.

7. The apparatus of claim 1 , wherein the pixel detection unit is further configured to detect light reflected from the rear reflector of the preceding vehicle by using a value of reflection intensity of light from a pre-learned cat's eye and a value of reflection intensity from the rear reflector.

8. The apparatus of claim 1 , wherein the image sensor comprises a light detection and ranging (LIDAR) sensor which is configured to generate reception intensity of light reflected from the preceding vehicle as 3-dimensional (3D) image information.

9. A method of detecting a preceding vehicle, comprising:
generating image information containing information on reception intensity of light reflected from a preceding vehicle;
detecting pixel areas corresponding to light reflected from rear reflectors of the preceding vehicle from the generated image information;
grouping adjacent pixel areas among the detected pixel areas;
classifying a kind of vehicle of the preceding vehicle by using at least one element of information between the information on a number of the grouped pixel areas and information on an interval; and
determining an operation point of an autonomous emergency braking (AEB) system of a host vehicle according to the classified kind of vehicle.

10. The method of claim 9 , wherein the classifying of the kind of vehicle of the preceding vehicle comprises classifying the preceding vehicle as a two-wheel vehicle, in response to the number of grouped pixel areas being one.

11. The method of claim 9 , wherein the classifying of the kind of vehicle of the preceding vehicle comprises classifying the preceding vehicle as a four-wheel vehicle, in response to the number of grouped pixel areas being two and an interval between the grouped pixel areas falling within rear reflector reference interval range.

12. The method of claim 9 , wherein the classifying of the kind of vehicle of the preceding vehicle comprises classifying a group comprising a second largest interval among the intervals between the grouped pixel areas as the group of rear reflectors of the four-wheel vehicle, in response to the number of grouped pixel areas being three.

13. The method of claim 9 , wherein the classifying of the kind of vehicle of the preceding vehicle comprises classifying the preceding vehicle as any one of a small-size vehicle, a midsize vehicle, and a full-size vehicle according to the information on the interval between the grouped pixel areas.

14. The method of claim 9 , wherein the determining of the operation point of the AEB system of the host vehicle comprises calculating a difference in a grade value between the preceding vehicle and the host vehicle with reference to a table, in which grades of the kind of vehicle are numerically expressed, and determining an operation point of the AEB system of the host vehicle according to a result of the calculation.

15. The method of claim 9 , wherein the detecting of the pixel areas corresponding to the light reflected from the rear reflectors of the preceding vehicle comprises detecting light reflected from the rear reflector of the preceding vehicle by using a value of reflection intensity of light from a pre-learned cat's eye and a value of reflection intensity from the rear reflector.

16. A method of detecting a preceding vehicle, comprising:
generating image information containing information on reception intensity of light reflected from a preceding vehicle;
detecting pixel areas corresponding to light reflected from rear reflectors of the preceding vehicle from the generated image information;
grouping adjacent pixel areas among the detected pixel areas;
classifying a kind of vehicle of the preceding vehicle by using at least one element of information between the information on the number of grouped pixel areas and information on an interval; and
determining an operation point of an autonomous emergency braking (AEB) system of a host vehicle according to the classified kind of vehicle,
wherein the classifying of the kind of vehicle of the preceding vehicle comprises classifying the preceding vehicle into a two-wheel vehicle, in response to the number of grouped pixel areas being one.

Assignees

• Hyundai Mobis Co Ltd

Inventors

• Kim Won Gyum

Classifications

• G01S17/931

  of land vehicles · CPC title

• G01S17/894

  Three-dimensional [3D] imaging with simultaneous measurement of time-of-flight at a two-dimensional [2D] array of receiver pixels, e.g. time-of-flight cameras or flash lidar · CPC title

• B60T7/22 Primary

  initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle {, or by means of contactless obstacle detectors mounted on the vehicle} · CPC title

• B60T2201/02

  Active or adaptive cruise control system; Distance control · CPC title

• G01S7/4802 Primary

  using analysis of echo signal for target characterisation; Target signature; Target cross-section · CPC title