Traffic congestion measuring method and apparatus and image processing method and apparatus

• US 6,075,874 A
• Filed: 03/11/1999
• Issued: 06/13/2000
• Est. Priority Date: 01/12/1996
• Status: Expired due to Term

• Current Assignee: Sumitomo Electric Industries Limited (Sumitomo Corporation)
• Original Assignee: Sumitomo Electric Industries Limited (Sumitomo Corporation)
• Inventors: Ito, Yoshiyuki, Higashikubo, Masakatsu
• Primary Examiner(s): Johns, Andrew W.
• Application Number:
  US09/265,980
• Time in Patent Office: 460 Days
• Field of Search: 382/104, 382/107, 382/173, 382/180, 382/291, 348/149, 701/117, 701/118, 701/119, 340/933, 340/934, 340/936, 340/937
• US Class Current: 382/104
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G08G 1/0104 Measuring and analyzing of parameters relative to traffic conditions
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors

Abstract

The present invention measures traffic congestion by utilizing a video camera to capture images of vehicles travelling on a road and analyzing sample points that are assigned to different aspects of the images. For example, presence and movement sample points correspond to the expected location and motion of the vehicles respectively. The sample points adjacent to one another form either movement or congestion blocks. The blocks that have a ratio of movement sample points to all other sample points within the block greater than a predetermined level are movement blocks. The remaining presence sample points in the images signify congestion sample points and form congestion blocks. Congestion blocks have a ratio of congestion sample points to all other sample points within the block greater than a predetermined level. Therefore, the state of traffic congestion is measured based upon the resultant movement and congestion blocks.

Claims

1. A traffic congestion measuring method of measuring a state of traffic congestion on the basis of a motion picture which represents a road and vehicles coming and going on said road and is formed by a series of images taken by a video camera, comprising the steps of:

(a) setting a plurality of sample points in said motion picture, each of said sample points having a brightness level;

(b) detecting, as presence sample points, the sample points which are situated in one of said series of images taken at a predetermined time and at each of which the vehicle is expected to be present;

(c) detecting, as movement sample points, the sample points which are situated in the image taken at said predetermined time and at each of which the vehicle in motion is expected to be present;

(d) detecting movement blocks each formed by part of the sample points adjacent to one another and including part of the movement sample points, a ratio of the movement sample points to all of the sample points contained in each movement block being larger than a predetermined level;

(e) detecting, as congestion sample points, the presence sample points excluded from said movement blocks;

(f) detecting congestion blocks each formed by part of the sample points adjacent to one another and including part of the congestion sample points, a ratio of the congestion sample points to all of the sample points contained in each congestion block being larger than a predetermined level; and

(g) measuring the state of traffic congestion on said road at said predetermined time on the basis of said congestion blocks.

2. A traffic congestion measuring method as set forth in claim 1, in which the sample points on a line perpendicular to a direction in which said road represented in the image extends are positioned in the image so as to correspond to actual locations, respectively, aligned at regular actual space intervals on said road,

the sample points on a line parallel to said direction are aligned at space intervals, and the space interval between two adjoining sample points aligned on the line parallel to said direction becoming smaller as two actual locations on said road respectively corresponding to said two adjoining sample points are more remote from said video camera.

3. A traffic congestion measuring method as set forth in claim 1, in which said step (b) comprises the steps of:

(b1) forming a criterion brightness image, in which no vehicle is expected to be present, taken by said video camera and represented only by picture elements corresponding to said sample points, respectively;

(b2) forming a sample point image represented only by picture elements respectively corresponding to said sample points included in the image at said predetermined time; and

(b3) detecting said presence sample points on the basis of said sample point image and said criterion brightness image.

4. A traffic congestion measuring method as set forth in claim 3, in which said steps (b) through (g) are repeated at regular time intervals,

said step (b) comprising the step of forming the criterion brightness image, which is utilized for detecting said presence sample points in the sample point image taken at time t1 corresponding to said predetermined time, on the basis of the sample point image taken at said time t1 and said criterion brightness image utilized for detecting said presence sample points in said sample point image taken at time t0 prior to said time t1 by one regular time interval.

5. A traffic congestion measuring method as set forth in claim 1, in which said step (b) comprises the steps of:

(b1) forming a criterion brightness image in which no vehicle is expected to be present and which is taken by said video camera;

(b2) calculating a difference image indicative of a difference in brightness between the image at said predetermined time and said criterion brightness image;

(b3) spatially differentiating said difference image;

(b4) detecting, as the presence sample points, the sample points each having a differentiation value larger than a predetermined threshold level in the spatially differentiated difference image, and

(b5) varying said threshold level, which is utilized for judging each of the sample points, in accordance with an actual route distance from said video camera to an actual location on said road corresponding to a position of each of the sample points in the image.

6. A traffic congestion measuring method as set forth in claim 1, in which said step (c) comprises the steps of:

(c1) forming a sample point image represented only by picture elements corresponding to the sample points in the image taken at time t corresponding to said predetermined time;

(c2) forming a sample point image represented only by picture elements corresponding to the sample points in the image taken at time t-α

, α

being a positive time interval;

(c3) forming a sample point image represented only by picture elements corresponding to the sample points in the image taken at time t+β

, β

being a positive time interval; and

(c4) detecting the movement sample points on the basis of said three sample point images respectively formed in said steps (c1), (c2) and (c3).

7. A traffic congestion measuring method as set forth in claim 1, in which said step (c) comprises the steps of:

(c1) calculating a first difference image indicative of a difference in brightness between the image taken at time t corresponding to said predetermined time and the image taken at time t-α

, α

being a positive time interval;

(c2) binarizing said first difference image with a first predetermined threshold level to form a first feature abstractive image containing only picture elements each having a level of "0" or "1";

(c3) calculating a second difference image indicative of a difference in brightness between the image taken at the time t and the image taken at time t+β

, β

being a positive time interval;

(c4) binarizing said second difference image with a second predetermined threshold level to form a second feature abstractive image containing only picture elements each having a level of "0" or "1";

(c5) calculating a product of said first feature abstractive image and said second feature abstractive image to form a product image;

(c6) detecting, as the movement sample points, the sample points corresponding to picture elements each having the level of "1" in said product image; and

(c7) varying the first and second predetermined threshold levels, which are utilized for judging each of the sample points, in accordance with an actual route distance from said video camera and an actual location on said road corresponding to a position of each of the sample points in the image.

8. A traffic congestion measuring method as set forth in claim 1, in which said step (d) comprises the steps of:

(d1) calculating movement sample point ratios each indicative of a ratio of the movement sample points to all of the sample points contained in each of candidate locks which partially forms the image taken at said predetermined time; and

(d2) detecting, as said movement blocks, the candidate blocks each having the calculated movement sample point ratio larger than a predetermined level.

9. A traffic congestion measuring method as set forth in claim 8, in which said step (d) comprises the step (d3) of varying, in size, each of said candidate blocks in accordance with an actual route distance from said video camera to an actual location on said road corresponding to a position of each of said candidate blocks in the image.

10. A traffic congestion measuring method as set forth in claim 8, in which said step (d) comprises the step (d3) of varying said predetermined level, which is utilized for judging each of said candidate blocks, in accordance with an actual route distance between said video camera to an actual location on said road corresponding to a position of each of said candidate blocks in the image.

11. A traffic congestion measuring method as set forth in claim 8, in which said step (d) comprises the step (d3) of removing, as noise, the movement sample points excluded from said movement blocks.

12. A traffic congestion measuring method as set forth in claim 1, in which said step (f) comprises the steps of:

(f1) calculating congestion sample point ratios indicative of a ratio of the congestion sample points to all of said sample points contained in each of candidate blocks which partially forms the image taken at said predetermined time; and

(f2) detecting, as said congestion blocks, the candidate blocks each having the calculated congestion sample point ratio larger than a predetermined level.

13. A traffic congestion measuring method as set forth in claim 12, in which said step (f) comprises the step (f3) of varying, in size, each of said candidate blocks in accordance with an actual route distance from said video camera to an actual location on said road corresponding to a position of each of said candidate blocks in the image.

14. A traffic congestion measuring method as set forth in claim 12, in which said step (f) comprises the step (f3) of varying said predetermined level, which is utilized for judging each of said candidate blocks, in accordance with an actual route distance from said video camera to an actual location on said road corresponding to a position of each of said candidate blocks in the image.

15. A traffic congestion measuring method as set forth in claim 12, in which said step (f) comprises the step (f3) of removing, as noise, the congestion sample points excluded from said congestion blocks.

16. A traffic congestion measuring method as set forth in claim 1, in which said step (g) comprises the step of judging an area occupied by a group of the congestion blocks in the image taken at said predetermined time to be a traffic congestion range on said road at said predetermined time.

17. A traffic congestion measuring apparatus for measuring a state of traffic congestion on the basis of a motion picture which represents a road and vehicles coming and going on said road and is formed by a series of images taken by a video camera, comprising:

first means for setting a plurality of sample points in said motion picture, each of said sample points having a brightness level;

second means for detecting, as presence sample points, the sample points which are situated in one of said series of images taken at a predetermined time and at each of which the vehicle is expected to be present;

third means for detecting, as movement sample points, the sample points which are situated in the image taken at said predetermined time and at each of which the vehicle in motion is expected to be present;

fourth means for detecting movement blocks each formed by part of the sample points adjacent to one another and including part of the movement sample points, a ratio of the movement sample points to all of the sample points contained in each movement block being larger than a predetermined level;

fifth means for detecting, as congestion sample points, the presence sample points excluded from said movement blocks;

sixth means for detecting congestion blocks each formed by part of the sample points adjacent to one another and including part of the congestion sample points, a ratio of the congestion sample points to all of the sample points contained in each congestion block being larger than a predetermined level; and

seventh means for measuring the state of traffic congestion on said road at said predetermined time on the basis of said congestion blocks.

18. A traffic congestion measuring apparatus as set forth in claim 17, in which said second means comprises:

means for forming a criterion brightness image in which no vehicle is expected to be present and which is taken by said video camera;

means for calculating a difference image indicative of a difference in brightness between the image taken at said predetermined time and said criterion brightness image;

means for spatially differentiating said difference image; and

means for detecting, as the presence sample points, the sample points each having a differentiation value larger than a predetermined threshold level in the spatially differentiated difference image,

said third means comprising;

means for calculating a first difference image indicative of a difference in brightness between the image taken at time t corresponding to said predetermined time and the image taken at time t-α

, α

being a positive time interval;

means for binarizing said first difference image with a first predetermined threshold level to form a first feature abstractive image containing only picture elements each having a level of "0" or "1";

means for calculating a second difference image indicative of a difference in brightness between the image taken at the time t and the image taken at time t+β

, β

being a positive time interval;

means for binarizing said second difference image with a second predetermined threshold level to form a second feature abstractive image containing only picture elements each having a level of "0" or "1";

means for calculating a product of said first feature abstractive image and said second feature abstractive image to form a product image; and

means for detecting, as the movement sample points, the sample points respectively corresponding to picture elements each having the level of "1" in said product image,

said fourth means comprising;

means for calculating movement sample point ratios each indicative of a ratio of the movement sample points to all of the sample points contained in each of candidate movement blocks which partially forms the image taken at said predetermined time; and

means for detecting, as said movement blocks, the candidate movement blocks each having the movement sample point ratio larger than said predetermined level used by said fourth means,

said sixth means comprising;

means for calculating congestion sample point ratios each indicative of a ratio of the congestion sample points to all of the sample points contained in each of candidate congestion blocks, said candidate congestion blocks each partially forming the image taken at said predetermined time; and

means for detecting, as said congestion blocks, the candidate congestion blocks each having the congestion sample point ratio larger than said predetermined level used by said sixth means, and

said seventh means judging an area occupied by a group of the congestion blocks in the image taken at said predetermined time to be a traffic congestion range on said road at said predetermined time.