Speed Calculation of a Moving Object based on Image Data

• US 20130322697A1
• Filed: 05/31/2012
• Published: 12/05/2013
• Est. Priority Date: 05/31/2012
• Status: Abandoned Application

• Current Assignee: Hexagon Technology Center GmbH (Hexagon AB)
• Original Assignee: Hexagon Technology Center GmbH (Hexagon AB)
• Inventors: Grindstaff, Gene A., Whitaker, Sheila G.
• Application Number:
  US13/485,369
• Publication Number:
  US 20130322697A1
• Time in Patent Office: Days
• US Class Current: 382/107
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20101 Interactive definition of point of interest, landmark or seed
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments

Abstract

A method and system for estimating the average speed of a moving object based on an attribute of the moving object present within the captured image data is disclosed. A plurality of images of the moving object are recorded using an image sensor that senses the ambient light or other electromagnetic radiation reflected or emitted by the moving object. Each image is captured at a different capture time. The image sensor is preferably located at a fixed or substantially fixed location when imaging the moving object. An area of interest of the moving object is located within the image data of the first image. An attribute of the moving object is then calculated for the first image. For at least a second image, the same attribute is calculated for the same area of interest of the moving object. The attribute calculations for the first and at least second images are then used to determine the average speed of the moving object. The attribute may be the cross-sectional area of the area of interest of the moving object.

Claims

1. A method for estimating speed of a moving object based upon a plurality of digital images comprising digital image data taken of the moving object from a substantially fixed position, where each image is captured at a different point in time, the method comprising:

identifying digital image data associated with an attribute of the moving object from a first digital image;

identifying image data associated with the attribute of the moving object from a second digital image; and

determining the speed of the moving object based upon the digital data associated with the attribute from the first and second digital images and the associated capture times.

2. A method according to claim 1 wherein the attribute relates solely to the moving object and is not related to the environment in which the object is moving.

3. A method according to claim 1 wherein the speed of the moving object is measured without determining any distance measurements between the substantially fixed position and the moving object.

4. A method according to claim 1 wherein the attribute is a geometric value for a portion of the moving object.

5. A method according to claim 1, wherein the attribute of the moving object varies with the speed of the moving object.

6. A method according to claim 1, wherein the digital image data representative of the object is automatically selected based upon at least a determination of a unique color range within the digital image data.

7. A method according to claim 1, wherein all digital image data for the attribute of the moving object below a threshold value are discarded prior to determining the speed of the moving object.

8. A method according to claim 1, further comprising:

determining a hue for the digital image data associated with the attribute of the moving object for at least the second digital image.

9. A method according to claim 8, wherein the determined hue is used to determine a tolerance range outside of which digital image data associated with the attribute from the first image and the second images are discarded.

10. A method according to claim 9, wherein remaining digital image data for the attribute associated with the moving object from the first image and the second images are used to determine a change in area of the attribute.

11. A method according to claim 9, wherein the change in area of the attribute is used in calculating the speed of the object.

12. A method according to claim 1, wherein the step of determining the speed is performed by a linear regression curve fitting of the digital image data for the attribute from at least the first image and the second image.

13. A method according to claim 1, further comprising:

determining the transmitivity for the digital image data associated with the moving object in at least the first image and the second image, wherein the attribute of the moving object is the transmitivity associated with the image data at a pixel location.

14. A method according to claim 13, wherein determining the speed uses the determined transmitivity and calculates distance measurements between the substantially fixed location and the moving object at each capture time.

15. A computer program product including a non-transitory computer readable medium having computer code thereon for estimating the average speed of a moving object, the computer code comprising:

computer code for accessing a plurality of images of the moving object from a fixed position wherein each image is captured at a different capture time;

for each image;

computer code for selecting image data representative of the object;

computer code for determining image data associated with an attribute of the object; and

computer code for calculating a speed measurement of the moving vehicle based at least upon the image data associated with the attribute of the moving object for each image and the associated capture time.

16. A computer program product according to claim 15 wherein the selection of the image data representative of an attribute of the object is performed automatically.

17. A computer program product according to claim 15, wherein the image data representative of the object may be a portion of the object.

18. A computer program product according to claim 15, wherein the attribute of the object is the cross-sectional area of a portion of the object.

19. A computer program product according to claim 18 wherein image data associated with the attribute is automatically selected based upon at least a determination of a unique color range for the image data of the attribute.

20. A computer program product according to claim 15, further comprising:

computer code for determining a hue for the image data associated with the attribute of the moving object for at least a second image.

21. A computer program product according to claim 20, wherein the determined hue is used to determine a tolerance range outside of which image data associated with the attribute from a first image and the second images are discarded.

22. A computer program product according to claim 21, wherein remaining digital image data for the attribute associated with the moving object from the images are used to determine a change in area of the attribute.

23. A computer program product according to claim 22, wherein the change in area of the attribute between images is used in calculating the speed of the object.

24. A computer program product according to claim 15, wherein the computer code for calculating the speed is performed by a linear regression curve fitting of the digital image data for the attribute for the images.

25. A computer program product according to claim 15, further comprising:

computer code for determining the transmitivity for the image data associated with the attribute of the moving object, wherein the attribute of the moving object is the transmitivity associated with the image data at a pixel location.

26. A computer program product according to claim 25, wherein the computer code for determining the speed uses the determined transmitivity and includes computer code for calculating distance measurements between the substantially fixed location and the moving object at each capture time.

27. A method for estimating the average speed of a moving object, the method comprising:

recording digital image data representative of at least a selected portion of the object at a first time from a substantially fixed position;

recording digital image data representative of at least the selected portion of the object at a second time from the substantially fixed position;

determining a cross-sectional area based on the digital image data for the selected portion of the object at the first time and the second time; and

calculating an average speed of the object based upon the determined cross-sectional area of the portion of the object and the associated capture times for the images.

28. The method according to claim 27 wherein recording a plurality of images is performed using a camera coupled to a base.

29. The method according to claim 28 wherein the base is a tripod

30. The method according to claim 27 wherein recording the digital data is performed using a camera held by a user.

31. The method according to claim 27, wherein the camera is part of a portable electronic device

32. The method according to claim 27, further comprising:

displaying the speed of the object on a display of an electronic device

33. The method according to claim 27 wherein the recording device includes a display, the display having a plurality of pixel locations.

34. The method according to claim 27 wherein the portion of the object at the first time is predefined by an area of the display defined by the pixel locations.

35. A method according to claim 27, further comprising:

determining hue of the portion of the object at the first time.

36. A method according to claim 27 wherein determining the cross-sectional area further comprises determining the hue of the digital image data for the portion of the object.

37. A method according to claim 36, further comprising:

eliminating digital image data outside of a range based upon the determined hue.

38. A method according to claim 37 wherein determining the cross-sectional area for a portion of the object is done based upon the digital image data remaining after eliminating digital data outside of the range.