METHOD AND APPARATUS FOR DETECTING A TRAFFIC STATE AND ELECTRONIC EQUIPMENT

• US 20170109892A1
• Filed: 10/14/2016
• Published: 04/20/2017
• Est. Priority Date: 10/14/2015
• Status: Abandoned Application

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: WU, Jianrong, TAN, Zhiming
• Application Number:
  US15/293,540
• Publication Number:
  US 20170109892A1
• Time in Patent Office: Days
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors

Abstract

A method and apparatus for detecting a traffic state and electronic equipment where the apparatus includes: a first calculating unit configured to detect a contour of an object from a region of interest of a traffic surveillance image to generate a contour image, and calculate an occupation ratio of the contour in the region of interest based on the contour image; a first detecting unit configured to detect whether there exists an object of a predetermined size moving in the region of interest, and determine a motion state of a vehicle in the region of interest; and a first determining unit configured to determine a traffic state according to the occupation ratio and the motion state. The embodiments of the present disclosure determine a traffic state according to the number of vehicles and motion states of the vehicles in the traffic surveillance image.

Claims

1. An apparatus for detecting a traffic state, comprising:

a first calculating unit configured to detect a contour of an object from a region of interest of a traffic surveillance image to generate a contour image, and calculate an occupation ratio of the contour in the region of interest based on the contour image;

a first detecting unit configured to detect whether there exists a moving object of a predetermined size moving in the region of interest, and determine a motion state of a vehicle in the region of interest; and

a first determining unit configured to determine the traffic state according to the occupation ratio and the motion state.

2. The apparatus for detecting the traffic state according to claim 1, wherein the first calculating unit comprises a first generating unit, when the traffic surveillance image is a color image, the first generating unit being configured to one of:

perform edge extraction processing on color components of the region of interest respectively to form edge detection images of the color components respectively, and combine the edge detection images of the color components, to generate the contour image; and

,

transform the color image into a grayscale image, perform edge extraction processing in the region of interest to form an edge detection image of the grayscale image, and use the edge detection image of the grayscale image as the contour image.

3. The apparatus for detecting the traffic state according to claim 1, wherein the first calculating unit comprises:

a second generating unit configured to, when the traffic surveillance image is a grayscale image, perform edge extraction processing on the region of interest to form an edge detection image, and use the edge detection image as the contour image.

4. The apparatus for detecting the traffic state according to claim 1, wherein the first calculating unit comprises:

a second calculating unit configured to calculate a pixel ratio of a contour number of pixels of the contour in the contour image to a total number of pixels in the region of interest, and use the pixel ratio as the occupation ratio.

5. The apparatus for detecting the traffic state according to claim 1, wherein,

the first detecting unit detects a foreground image of the region of interest of the traffic surveillance image, and judges whether there exists the moving object of the predetermined size in the foreground image.

6. The apparatus for detecting the traffic state according to claim 1, wherein,

when there exists the moving object of the predetermined size moving in the region of interest of the traffic surveillance image of a current frame, the first detecting unit judges whether there exists the moving object of the predetermined size moving in regions of interest in a first predetermined number of frames preceding the current frame, and if yes, determines that the vehicle in the region of interest of the traffic surveillance image of the current frame is in a state of movement, otherwise, determines that the vehicle in the region of interest of the traffic surveillance image of the current frame is in a static state.

7. The apparatus for detecting the traffic state according to claim 1, wherein,

when there exists no moving object of the predetermined size moving in the region of interest of the traffic surveillance image of a current frame, the first detecting unit determines that the vehicle in the region of interest of the traffic surveillance image of the current frame is in a static state.

8. The apparatus for detecting the traffic state according to claim 1, wherein the first determining unit:

calculates first parameters of the traffic surveillance images of a current frame and a second predetermined number of frames preceding the current frame according to motion states of vehicles in the region of interest of the current frame and the second predetermined number of frames preceding the current frame and a relationship between the occupation ratio and a threshold value; and

performs an operation on the first parameters of the current frame and the second predetermined number of frames preceding the current frame, and determines according to a relationship between a result of the operation and a second parameter that the traffic state to which the traffic surveillance image of the current frame corresponds is jammed, that one of a vehicle flow-rate is smooth flow and the a vehicle flow-rate is heavy flow.

9. The apparatus for detecting the traffic state according to claim 8, wherein,

the threshold value is related to the motion state.

19. Electronic equipment, comprising the apparatus for detecting the traffic state as described in claim 1.

10. A method for detecting a traffic state, comprising:

detecting a contour of an object from a region of interest of a traffic surveillance image to generate a contour image, and calculating an occupation ratio of the contour in the region of interest based on the contour image;

detecting whether there exists a moving object of a predetermined size moving in the region of interest, and determining a motion state of a vehicle in the region of interest; and

determining the traffic state according to the occupation ratio and the motion state.

11. The method for detecting the traffic state according to claim 10, wherein when the traffic surveillance image is a color image, the detecting the contour of then object to generate a contour image comprises one of:

performing edge extraction processing on color components of the region of interest respectively to form edge detection images of the color components respectively, and combine the edge detection images of the color components to generate the contour image; and

,

transforming the color image into a grayscale image, performing edge extraction processing in the region of interest to form an edge detection image of the grayscale image, and using the edge detection image of the grayscale image as the contour image.

12. The method for detecting the traffic state according to claim 10, wherein when the traffic surveillance image is a grayscale image, the detecting a contour of the object to generate a contour image comprises:

performing edge extraction processing on the region of interest to form an edge detection image, and using the edge detection image as the contour image.

13. The method for detecting the traffic state according to claim 10, wherein the calculating the occupation ratio based on the contour image comprises:

calculating a pixel ratio of a contour number of pixels of the contour in the contour image to a total number of pixels in the region of interest, and using the pixel ratio as the occupation ratio.

14. The method for detecting the traffic state according to claim 10, wherein the detecting whether there exists a the moving object of a predetermined size moving in the region of interest comprises:

detecting a foreground image of the region of interest of the traffic surveillance image; and

judging whether there exists the the object of the predetermined size in the foreground image.

15. The method for detecting the traffic state according to claim 10, wherein the determining the motion state of the vehicle in the region of interest comprises:

when there exists the moving object of the predetermined size moving in the region of interest of the traffic surveillance image of a current frame, judging whether there exists the moving object of the predetermined size moving in regions of interest in a first predetermined number of frames preceding the current frame, and if yes, determining that the vehicle in the region of interest of the traffic surveillance image of the current frame is in a state of movement, otherwise, determining that the vehicle in the region of interest of the traffic surveillance image of the current frame is in a static state.

16. The method for detecting the traffic state according to claim 10, wherein the determining the motion state of a vehicle in the region of interest comprises:

when there exists no moving object of the predetermined size moving in the region of interest of the traffic surveillance image of the current frame, determining that the vehicle in the region of interest of the traffic surveillance image of the current frame is in a static state.

17. The method for detecting the traffic state according to claim 10, wherein the determining the traffic state according to the occupation ratio and the motion state comprises:

calculating first parameters of the traffic surveillance images of the current frame and a second predetermined number of frames preceding the current frame according to motion states of vehicles in the region of interest of the current frame and the second predetermined number of frames preceding the current frame and a relationship between the occupation ratio and a threshold value; and

performing an operation on the first parameters of the current frame and the second predetermined number of frames preceding the current frame, and determines according to a relationship between a result of the operation and a second parameter that the traffic state to which the traffic surveillance image of the current frame corresponds is jammed, one of a vehicle flow-rate is smooth flow and the vehicle flow-rate is heavy flow.

18. The method for detecting the traffic state according to claim 17, wherein,

the threshold value is related to the motion state.

20. A non-transitory computer readable storage storing a method according to claim 10.

21. An apparatus for detecting a traffic state, comprising:

a computer and a memory, comprising;

a first calculating unit configured to detect a contour of an object from a region of interest of a traffic surveillance image to generate a contour image, and calculate an occupation ratio of the contour in the region of interest based on the contour image;

a first detecting unit configured to detect whether there exists a moving object of a predetermined size moving in the region of interest, and determine a motion state of a vehicle in the region of interest; and

a first determining unit configured to determine a traffic state according to the occupation ratio and the motion state.