Methods and systems for identifying events for a vehicle

• US 7,809,164 B2
• Filed: 01/10/2007
• Issued: 10/05/2010
• Est. Priority Date: 01/10/2007
• Status: Active Grant

• Current Assignee: MAVS Lab Incorporated
• Original Assignee: MAVS Lab Incorporated
• Inventors: Yeh, Chia-Hung, Shih, Hsuan-Huei
• Primary Examiner(s): CHANG, JON CARLTON
• Application Number:
  US11/621,577
• Publication Number:
  US 20080166050A1
• Time in Patent Office: 1,364 Days
• Field of Search: 382/103, 382/104, 340/933, 340/937, 340/435, 340/436, 348/113
• US Class Current: 382/104
• 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: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles

Abstract

A system for identifying an event for a vehicle is disclosed. The system includes: a video source; a receiving circuit, coupled to the video source, for receiving at least a target image from the video source positioned on the vehicle; and a determining circuit, coupled to the receiving circuit, for determining if the event occurs according to the target image. A related method includes: receiving at least a target image from a video source positioned on the vehicle; and determining if the event occurs according to the target image.

Claims

1. A method for identifying an event for a vehicle, the method comprising:

receiving at least a target image from a video source positioned on the vehicle;

selecting at least a predetermined image region from the target image;

receiving a plurality of images prior to the target image;

determining a reference statistical value of the predetermined image region according to image information of the predetermined image region in each of the images; and

comparing a statistical value of the predetermined image in the target image with the reference statistical value to determine if the event occurs;

wherein if a difference between the reference statistical value and the statistical value is greater than a threshold value, determining that the event occurs.

2. The method of claim 1, wherein the step of determining the reference statistical value comprises:

averaging a plurality of statistical values corresponding to the predetermined image region in the images to generate the reference statistical value.

3. The method of claim 2, wherein each statistical value is a variance, a mean, or a moment.

4. The method of claim 1, wherein a selection of the images prior to the target image is updated as the target image is changed.

5. The method of claim 1, further comprising:

preprocessing the target image before executing the step of determining if the event occurs.

6. A method for identifying an event for a vehicle, the method comprising:

receiving at least a target image from a video source positioned on the vehicle;

selecting a scanline from the target image;

receiving a plurality of images prior to the target image;

determining reference pixel values of pixels at the scanline according to image information of the scanline in each of the images; and

comparing pixel values of the pixels at the scanline in the target image with the reference pixel values to determine if the event occurs.

7. The method of claim 6, wherein the step of determining the reference pixel values comprises:

averaging a plurality of pixel values corresponding to the pixels at the scanline in the images to generate the reference pixel values.

8. The method of claim 6, wherein the step of comparing the pixel values of the scanline in the target image with the reference pixel values further comprises:

if a ratio of a sum of pixel differences between the reference pixel values and the pixel values to a sum of the reference pixel values is greater than a threshold value, determining that the event occurs.

9. The method of claim 6, wherein a selection of the images prior to the target image is updated as the target image is changed.

10. The method of claim 6, wherein the step of analyzing the scanline of the target image comprises:

receiving a plurality of images prior to the target image;

utilizing a reference value to binarize pixel values of all pixels at the scanline in each of the images to identify specific pixels in each of the images that have pixel values greater than the reference value;

utilizing the specific pixels in each of the images to determine a reference position;

utilizing the reference value to binarize pixel values of all pixels at the scanline in the target image to identify specific target pixels having pixel values greater than the reference value;

utilizing the specific target pixels in each of the images to determine a position;

comparing the reference position with the position to determine if the event occurs.

11. The method of claim 10, wherein the step of utilizing the specific pixels in each of the images to determine the reference position comprises:

determining a specific position corresponding to each of the images according to the specific pixels in each of the images; and

averaging a plurality of specific positions corresponding to the images to generate the reference position.

12. The method of claim 10, wherein the step of comparing the reference position with the position further comprises:

if a difference between the reference position and the position is greater than a threshold, determining that the event occurs.

13. The method of claim 10, wherein a selection of the images prior to the target image is updated as the target image is changed.

14. The method of claim 6, further comprising:

preprocessing the target image before executing the step of determining if the event occurs.

15. A system for identifying an event for a vehicle, the system comprising:

a video source;

a receiving circuit, coupled to the video source, for receiving at least a target image from the video source positioned on the vehicle; and

a determining circuit, coupled to the receiving circuit, for determining if the event occurs according to the target image, comprising;

a selecting circuit, for selecting at least a predetermined image region from the target image; and

an analyzing circuit, coupled to the selecting circuit, for analyzing the predetermined image region to determine if the event occurs, comprising;

a buffer circuit, coupled to the selecting circuit, for receiving a plurality of images prior to the target image;

a reference statistical value determining circuit, coupled to the buffer circuit, for determining a reference statistical value of the predetermined image region according to image information of the predetermined image region in each of the images; and

a comparing circuit, coupled to the selecting circuit and the reference statistical value determining circuit, for comparing a statistical value of the predetermined image in the target image with the reference statistical value to determine if the event occurs, wherein if a difference between the reference statistical value and the statistical value is greater than a threshold value, the comparing circuit determines that the event occurs.

16. The system of claim 15, wherein the reference statistical value determining circuit comprises:

an averaging circuit, for averaging a plurality of statistical values corresponding to the predetermined image region in the images to generate the reference statistical value.

17. The system of claim 16, wherein each statistical value is a variance, a mean, or a moment.

18. The system of claim 15, wherein a selection of the images prior to the target image is updated as the target image is changed.

19. The system of claim 15, further comprising:

a preprocessing circuit, coupled to the receiving circuit, for preprocessing the target image.

20. A system for identifying an event for a vehicle, the system comprising:

a video source;

a receiving circuit, coupled to the video source, for receiving at least a target image from the video source positioned on the vehicle; and

a determining circuit, coupled to the receiving circuit, for determining if the event occurs according to the target image, comprising;

a selecting circuit, for selecting a scanline from the target image;

an analyzing circuit, coupled to the selecting circuit, for analyzing the scanline of the target image to determine if the event occurs, comprising;

a buffer circuit, coupled to the selecting circuit, for receiving a plurality of images prior to the target image;

a reference statistical value determining circuit, coupled to the buffer circuit, for determining reference pixel values of pixels at the scanline according to image information of the scanline in each of the images; and

a comparing circuit, coupled to the selecting circuit and the reference statistical value determining circuit, for comparing pixel values of the pixels at the scanline in the target image with the reference pixel values to determine if the event occurs.

21. The system of claim 20, wherein the reference statistical value determining circuit comprises:

an averaging circuit, for averaging a plurality of pixel values corresponding to the pixels at the scanline in the images to generate the reference pixel values.

22. The system of claim 20, wherein if a ratio of a sum of pixel differences between the reference pixel values and the pixel values to a sum of the reference pixel values is greater than a threshold value, the comparing circuit determines that the event occurs.

23. The system of claim 20, wherein a selection of the images prior to the target image is updated as the target image is changed.

24. The system of claim 20, wherein the analyzing circuit comprises:

a buffer circuit, coupled to the selecting circuit, for receiving a plurality of images prior to the target image;

a first binarizing circuit, coupled to the buffer circuit, for utilizing a reference value to binarize pixel values of all pixels at the scanline in each of the images to identify specific pixels in each of the images that have pixel values greater than reference value;

a first position determining circuit, coupled to the first binarizing circuit, for utilizing the specific pixels in each of the images to determine a reference position;

a second binarizing circuit, coupled to the selecting circuit, for utilizing the reference value to binarize pixel values of all pixels at the scanline in the target image to identify specific target pixels having pixel values greater than the reference value;

a second position determining circuit, coupled to the second binarizing circuit, for utilizing the specific target pixels in each of the images to determine a position;

a comparing circuit, coupled to the first position determining circuit and the second position determining circuit, for comparing the reference position with the position to determine if the event occurs.

25. The system of claim 24, wherein the first position determining circuit comprises:

a position information determining circuit, for determining a specific position corresponding to each of the images according to the specific pixels in each of the images; and

an averaging circuit, coupled to the position information determining circuit, for averaging a plurality of specific positions corresponding to the images to generate the reference position.

26. The system of claim 24, wherein if a difference between the reference position and the position is greater than a threshold, the comparing circuit determines that the event occurs.

27. The system of claim 24, wherein a selection of the images prior to the target image is updated as the target image is changed.

28. The system of claim 20, further comprising:

a preprocessing circuit, coupled to the receiving circuit, for preprocessing the target image.

29. A method for identifying an event for a vehicle, the method comprising:

receiving at least a target image from a video source positioned on the vehicle;

selecting at least a predetermined image region from the target image;

receiving a plurality of images prior to the target image;

determining a reference statistical value of the predetermined image region according to image information of the predetermined image region in each of the images, comprising;

averaging a plurality of statistical values corresponding to the predetermined image region in the images to generate the reference statistical value; and

comparing a statistical value of the predetermined image in the target image with the reference statistical value to determine if the event occurs.

30. The method of claim 29, wherein each statistical value is a variance, a mean, or a moment.

31. The method of claim 29, wherein the step of comparing the statistical value of the predetermined image in the target image with the reference statistical value further comprises:

if a difference between the reference statistical value and the statistical value is greater than a threshold value, determining that the event occurs.

32. The method of claim 29, wherein a selection of the images prior to the target image is updated as the target image is changed.

33. A system for identifying an event for a vehicle, the system comprising:

a video source;

a receiving circuit, coupled to the video source, for receiving at least a target image from the video source positioned on the vehicle; and

a determining circuit, coupled to the receiving circuit, for determining if the event occurs according to the target image, comprising;

a selecting circuit, for selecting at least a predetermined image region from the target image; and

an analyzing circuit, coupled to the selecting circuit, for analyzing the predetermined image region to determine if the event occurs, comprising;

a buffer circuit, coupled to the selecting circuit, for receiving a plurality of images prior to the target image;

a reference statistical value determining circuit, coupled to the buffer circuit, for determining a reference statistical value of the predetermined image region according to image information of the predetermined image region in each of the images, wherein the reference statistical value determining circuit comprises;

an averaging circuit, for averaging a plurality of statistical values corresponding to the predetermined image region in the images to generate the reference statistical value; and

a comparing circuit, coupled to the selecting circuit and the reference statistical value determining circuit, for comparing a statistical value of the predetermined image in the target image with the reference statistical value to determine if the event occurs.

34. The system of claim 33, wherein each statistical value is a variance, a mean, or a moment.

35. The system of claim 33, wherein if a difference between the reference statistical value and the statistical value is greater than a threshold value, the comparing circuit determines that the event occurs.

36. The system of claim 33, wherein a selection of the images prior to the target image is updated as the target image is changed.