Traffic-counting system and method thereof

Patent metadata

Field	Value
Publication number	US-10248870-B2
Application number	US-201615205236-A
Country	US
Kind code	B2
Filing date	Jul 8, 2016
Priority date	Jun 29, 2016
Publication date	Apr 2, 2019
Grant date	Apr 2, 2019

Abstract

Traffic-counting methods and apparatus are disclosed. The methods may include, in a view of traffic comprising moving objects, identifying first and second regions of interest (ROIs). The methods may also include obtaining first and second image data respectively representing the first and second ROIs. The methods may also include analyzing the first and second image data over time. The methods may further include, based on the analyses of the first and second image data, counting the moving objects and determining moving directions of the moving objects.

First claim

What is claimed is:

1. A traffic-counting method performed by a processor in communication with an imaging device, comprising:
in a view of traffic comprising moving objects, identifying first and second regions of interest (ROIs);
obtaining, from the imaging device, first and second image data respectively representing the first and second ROIs;
analyzing the first and second image data over time; and
based on the analyses of the first and second image data:
counting the moving objects; and
determining moving directions of the moving objects,
wherein the counting and determining comprise:
detecting that a first foreground begins to appear in the first ROI:
when detecting that a second foreground begins to appear in the second ROI within a first amount of time after the first foreground begins to appear, determining whether a color of the first foreground is consistent with a color of the second foreground; and
when it is determined that the colors of the first and second foregrounds are consistent, concluding that one or more moving objects are moving from the first ROI to the second ROI.

2. The method of claim 1 , wherein the first and second ROIs correspond to different portions of an area where the traffic occurs.

3. The method of claim 1 , wherein identifying the first and second ROIs further comprises:
setting sizes of the first and second ROIs based on volume of the traffic.

4. The method of claim 1 , wherein:
the analyzing comprises comparing, over time, a value of a property of the first ROI with a value of the property of the second ROI; and
the counting and determining comprise counting the moving objects and determining the moving directions of the moving objects, based on a result of the comparison.

5. The method of claim 4 , wherein the property comprises at least one of:
a brightness of the respective ROI; or
a color of the respective ROI.

6. The method of claim 1 , further comprising:
when detecting that the color of the first foreground changes N times, concluding that (N+1) moving objects are moving from the first ROI to the second ROI, N being an integer greater than or equal to zero.

7. The method of claim 1 further comprising:
determining the first amount of time based on a distance separating the first and second ROIs.

8. The method of claim 1 , wherein detecting the first foreground further comprises:
obtaining reference data representing the first ROI in a time when no moving objects are present in the first ROI;
determining a difference between the first image data and the reference data; and
when the difference exceeds a predetermined data threshold, determining the difference as the first foreground.

9. The method of claim 8 , further comprising:
when the difference does not exceed the data threshold, updating the reference data based on the first image data.

10. The method of claim 8 , further comprising:
when determining that the first foreground has appeared for longer than a second amount of time, updating the reference data based on the first image data.

11. The method of claim 10 , wherein:
the first image data represents a plurality of image frames; and
determining that the first foreground has appeared for longer than a second amount of time comprises:
determining that a number of consecutive image frames containing the first foreground exceeds a predetermined number.

12. The method of claim 1 , wherein determining that the colors of the first and second foregrounds are consistent comprises:
determining a first color value indicative of the color of the first foreground when the first foreground begins to appear;
determining a second color value indicative of the color of the second foreground when the second foreground begins to appear; and
when determining that the first and second color values differ by less than a predetermined color threshold, determining that the colors of the first and second foregrounds are consistent.

13. The method of claim 1 , wherein counting the moving objects and determining moving directions of the moving objects comprise:
determining a feature of the traffic based on a result of the counting and the determined moving directions.

14. The method of claim 13 , wherein:
the traffic occurs on a pathway towards a place of interest; and
determining the feature of the traffic comprises:
counting, after a predetermined point in time, a first number of moving objects moving in a first direction and a second number of moving objects moving in a second direction; and
when the first number reaches a predetermined value earlier than the second number, determining that the moving objects moving in the first direction are moving toward the place of interest.

15. A traffic-counting device, comprising:
a memory storing instructions; and
a processor in communication with an imaging device, the processor being configured to execute the instructions to:
in a view of traffic comprising moving objects, identify first and second regions of interest (ROIs);
obtain, from the imaging device, first and second image data respectively representing the first and second ROIs;
analyze the first and second image data over time; and
based on the analyses of the first and second image data:
count the moving objects; and
determine moving directions of the moving objects,

wherein in counting the moving objects and determining the moving directions of the moving objects, the processor is further configured to execute the instructions to:
determine that a first foreground begins to appear in the first ROI:
determine whether a second foreground begins to appear in the second ROI within a first amount of time after the first foreground begins to appear;
when the second foreground begins to appear within the first amount of time, determine whether a color of the first foreground is consistent with a color of the second foreground; and
when the colors of the first and second foregrounds are consistent, conclude that one or more moving objects are moving from the first ROI to the second ROI.

16. The device of claim 15 , wherein the first and second ROIs correspond to different portions of an area where the traffic occurs.

17. The device of claim 15 , wherein the processor is further configured to execute the instructions to:
set sizes of the first and second ROIs based on volume of the traffic.

18. The device of claim 15 , wherein the processor is further configured to execute the instructions to:
determine whether the color of the first foreground changes; and
when determining that the color of the first foreground changes N times, conclude that (N+1) moving objects are moving from the first ROI to the second ROI, N being an integer greater than or equal to zero.

19. The device of claim 15 , wherein the processor is further configured to execute the instructions to:
determine the first amount of time based on a distance separating the first and second ROIs.

20. The device of claim 15 , wherein the processor is further configured to execute the instructions to:
obtain reference data representing the first ROI in a time when no moving objects are present in the first ROI;
determine a difference between the first image data and the reference data; and
when the difference exceeds a predetermined data threshold, determine the difference as the first foreground.

21. The device of claim 20 , wherein the processor is further configured to execute the instructions to:
when the d

Assignees

• Xiaoyi Tech Co Ltd
• Shanghai Xiaoyi Tech Co Ltd

Inventors

• Ding Dajun
• Zhao Lili

Classifications

• G06V20/54

  of traffic, e.g. cars on the road, trains or boats · CPC title

• G06V40/20 Primary

  Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title

• G06K9/4652

  Physics · mapped topic

• G06K9/00335

  Physics · mapped topic