OBJECT RECOGNITION SYSTEM, AND OBSTACLE RECOGNITION SYSTEM AND METHOD FOR VEHICLE

• US 20120127309A1
• Filed: 02/22/2011
• Published: 05/24/2012
• Est. Priority Date: 11/23/2010
• Status: Active Grant

• Current Assignee: Hyundai Mobis Co., Ltd.
• Original Assignee: Hyundai Mobis Co., Ltd.
• Inventors: LEE, Hong Seok
• Granted Patent: US 8,848,055 B2
• Time in Patent Office: Days
• US Class Current: 348/148
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• 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: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

Provided is an object recognition system. The object recognition system recognizes an object in an ROI of a source image. The object recognition system includes an image change unit and an ROI detection unit. The image change unit receives the source image, and changes the object into an edge image which is represented as an edge line. The ROI detection unit divides the edge image into a plurality of regions, compares a total sum of edge component values of an edge line included in each of the regions and a predetermined threshold value by regions, and detects a region, in which the total sum of edge component values is greater than the threshold value, as the ROI from among the plurality of regions.

Claims

1. An object recognition system which recognizes an object in a Region Of Interest (ROI) of a source image, the object recognition system comprising:

an image change unit receiving the source image, and changing the object into an edge image which is represented as an edge line; and

an ROI detection unit dividing the edge image into a plurality of regions, comparing a total sum of edge component values of an edge line comprised in each of the regions and a predetermined threshold value by regions, and detecting a region, in which the total sum of edge component values is greater than the threshold value, as the ROI from among the plurality of regions.

2. The object recognition system of claim 1, wherein the ROI detection unit divides an entire region of the edge image into n equal portions (where ‘

n’

is a natural number equal to or more than

     2) to divide into the plurality of regions.

3. The object recognition system of claim 2, wherein ‘

n’

is equal to or less than six.

4. An obstacle recognition system for vehicle, comprising:

an image photographing unit comprised in a vehicle, and generating a source image which is obtained by photographing a front view and a rear view while the vehicle is driving;

an edge image generation unit receiving the source image, and generating an edge image which represents an object comprised in the source image as an edge line;

a Region Of Interest (ROI) detection unit dividing the edge image into a plurality of regions, calculating a total sum of edge component values of the edge line for each region, comparing the total sum of edge component values and a predetermined threshold value, and detecting an ROI from the regions on the basis of the compared result for each region; and

an image analysis unit scanning the detected ROI by block units having a certain size to analyze whether an obstacle exists in the detected ROI.

5. The obstacle recognition system of claim 4, wherein the ROI detection unit comprises:

an image divider dividing the edge image in a horizontal direction to divide into the plurality of regions;

an edge value collector calculating a total sum of edge component values of an edge line which is comprised in each of the regions, and collecting the calculated total sum of edge component values by regions; and

a comparator receiving the predetermined threshold value, comparing the total sum of edge component values of the edge line and the threshold value for each region, and detecting a region, in which the total sum of edge component values is greater than the threshold value, as the ROI from among the plurality of regions.

6. The obstacle recognition system of claim 5, wherein when an entire size of the edge image is “

i*j”

(where ‘

i’

is the number of pixels in a horizontal direction, and ‘

j’

is the number of pixels in a vertical direction),

a size of each of the regions is “

i*(j/n)”

(where ‘

n’

is a natural number from two to six).

7. The obstacle recognition system of claim 4, wherein the edge image generation unit changes the source image into an intermediate image which is composed of an edge line of the object, and binarizes the changed intermediate image to generate the edge image having a grey gray scale.

8. The obstacle recognition system of claim 4, wherein the edge component values are gray scale values of pixels which configure the edge line.

9. An obstacle recognition system for vehicle, comprising:

an image photographing unit comprised in a vehicle, and generating a source image which is obtained by photographing a front view and a rear view while the vehicle is driving;

an edge image generation unit receiving the source image, and generating an edge image which represents an object comprised in the source image as an edge line;

a Region Of Interest (ROI) detection unit dividing the edge image into a predetermined number of regions according to a speed value of the vehicle, calculating a total sum of edge component values of the edge line for each region, comparing the total sum of edge component values and a predetermined threshold value for each region, and detecting an ROI from the regions on the basis of the compared result for each region; and

an image analysis unit scanning the detected ROI by block units having a certain size to analyze whether an obstacle exists in the detected ROI.

10. The obstacle recognition system of claim 9, wherein the ROI detection unit comprises:

an image divider receiving the speed value of the vehicle from a vehicle system, and dividing an entire region of the edge image into a predetermined number of regions according to the received speed value of the vehicle;

an edge value collector calculating a total sum of edge component values of an edge line which is comprised in each of the regions, and collecting the calculated total sum of edge component values by regions; and

a comparator comparing the total sum of edge component values of the edge line and the predetermined threshold value for each region, and detecting a region, in which the total sum of edge component values is greater than the threshold value, as the ROI from among the plurality of regions.

11. The obstacle recognition system of claim 10, wherein the image divider receives the speed value of the vehicle from the vehicle system in a Controller Area Network (CAN) communication scheme.

12. The obstacle recognition system of claim 10, wherein the image divider divides the edge image into n equal portions (where ‘

n’

is a natural number equal to or more than

     2) in a horizontal direction in a predetermined size according to the speed value of the vehicle.

13. The obstacle recognition system of claim 10, wherein when an entire size of the edge image is “

i*j”

(where ‘

i’

is the number of pixels in a horizontal direction, and ‘

j’

is the number of pixels in a vertical direction),

a size of each of the divided regions is “

i*(j/n)”

(where ‘

n’

is a natural number from two to six).

14. The obstacle recognition system of claim 13, wherein as a speed of the vehicle increases, ‘

n’

increases.

15. The obstacle recognition system of claim 9, wherein the edge image generation unit, the ROI detection unit and the image analysis unit are modularized in a chip type.

16. An obstacle recognition method for vehicle which scans a Region Of Interest (ROI) detected from a source image by block units having a certain size to recognize an obstacle, the obstacle recognition method comprising:

generating an edge image which represents an object comprised in the source image as an edge line;

dividing the edge image into a predetermined number of regions according to a speed value of the vehicle; and

calculating a total sum of edge component values of an edge line which exists in each of the divide regions, comparing the total sum of the edge component values and a predetermined threshold value, and detecting an ROI from the regions on the basis of the compared result for each region.

17. The obstacle recognition system of claim 16, wherein the edge image is divided in a horizontal direction.

18. The obstacle recognition system of claim 16, wherein as the speed value of the vehicle increases, the predetermined number increases.