Daytime and nighttime image recognizing method and apparatus

• US 8,204,305 B2
• Filed: 12/20/2007
• Issued: 06/19/2012
• Est. Priority Date: 12/29/2006
• Status: Expired due to Fees

• Current Assignee: Alpine Electronics Incorporated (Alps Alpine Co., Ltd.)
• Original Assignee: Alpine Electronics Incorporated (Alps Alpine Co., Ltd.)
• Inventors: Zou, Bo, Wang, Nan
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): Rush, Eric
• Application Number:
  US11/961,997
• Publication Number:
  US 20080159623A1
• Time in Patent Office: 1,643 Days
• Field of Search: 382/100, 382/103, 382/104, 382168-172, 382/194
• US Class Current: 382/170
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

In a daytime and nighttime image recognizing method and apparatus, the method comprises predefining an air region and a terrestrial region for each image captured by a camera apparatus; inputting an image captured by the camera apparatus; calculating a lightness value histogram for the air region of the input image; and determining a lighting condition of a photo environment of the camera apparatus based on the lightness value histogram for the air region of the input image. The daytime and nighttime image recognizing method and apparatus are able to correctly recognize the lighting condition of the environment even if the air region in an image is obstructed by a background or there are no lane lines in an image. Moreover, when an erroneous recognition occurs for an individual image, the interference caused by the erroneous recognition can be precluded efficiently.

Claims

1. A daytime and nighttime image recognizing method, comprising:

inputting an image captured by a camera apparatus;

predefining an air region and a terrestrial region for the input image captured by the camera apparatus;

calculating a lightness value histogram for the air region of the input image;

determining a lighting condition of a photo environment of the camera apparatus based on the lightness value histogram for the air region of the input image, wherein determining the lighting condition further includes;

judging whether a ratio of a number of pixels with lightness values larger than a first lightness value (T1) in the air region of the input image to the total number of pixels in the air region of the input image is greater than a first ratio; and

determining the photo environment of the camera apparatus as a daytime lighting condition if the judgment result is affirmative; and

wherein calculating the lightness value histogram and determining the lighting condition require no vehicle lane lines in the input image.

2. The method according to claim 1, wherein the first ratio is approximately 30%.

3. The method according to claim 1, further comprising:

if the judgment result is negative, further judging whether a ratio of a number of pixels with lightness values less than a second lightness value (T2) which is smaller than the first lightness value (T1) in the air region of the input image to the number of all pixels of the air region in the input image is greater than a second ratio, based on distribution information of the lightness value histogram for the air region of the input image; and

determining the photo environment of the camera apparatus as one of a dawn or dusk lighting condition, if the further judgment result is negative.

4. The method according to claim 3, wherein the second ratio is approximately 80%.

5. The method according to claim 3, further comprising:

calculating a lightness value histogram for the terrestrial region of the input image if the further judgment result is affirmative;

yet further judging whether a ratio of a number of pixels with lightness values larger than the first lightness value (T1) in the terrestrial region of the input image to the number of all pixels of the terrestrial region in the input image is greater than a third ratio, based on the lightness value histogram for the terrestrial region of the input image; and

determining the photo environment of the camera apparatus as the daytime lighting condition if the yet further judgment result is affirmative.

6. The method according to claim 5, wherein the third ratio is approximately 70%.

7. The method according to claim 5, further comprising:

additionally judging whether a ratio of a number of pixels with lightness values less than the second lightness value (T2) in the terrestrial region of the input image to the number of all pixels of the terrestrial region in the input image is greater than a fourth ratio, based on the lightness value histogram for the terrestrial region of the input image, if the yet further judgment result is negative; and

determining the photo environment of the camera apparatus as the nighttime lighting condition, if the result of the additional judging is affirmative.

8. The method according to claim 7, wherein the fourth ratio is approximately 80%.

9. The method according to claim 1, further comprising:

determining the lighting condition for the photo environment of the camera apparatus based on determined lighting conditions of a plurality of images captured by the camera apparatus.

10. The method according to claim 1, wherein the camera apparatus is mounted on one of a vehicle or a stationary object.

11. A daytime and nighttime image recognizing method, comprising:

inputting an image captured by a camera apparatus;

predefining an air region and a terrestrial region for the input image captured by the camera apparatus;

calculating a lightness value histogram for the air region of the input image;

determining a lighting condition of a photo environment of the camera apparatus based on the lightness value histogram for the air region of the input image;

wherein determining the lighting condition further comprises;

judging whether a ratio of a number of pixels with lightness values larger than a first lightness value (T1) in the air region of the input image to the total number of pixels in the air region of the input image is greater than a first ratio; and

determining the photo environment of the camera apparatus as a daytime lighting condition if the judgment result is affirmative.

12. The method according to claim 11, wherein the first ratio is approximately 30%.

13. The method according to claim 11, further comprising:

if the judgment result is negative, further judging whether a ratio of a number of pixels with lightness values less than a second lightness value (T2) which is smaller than the first lightness value (T1) in the air region of the input image to the number of all pixels of the air region in the input image is greater than a second ratio, based on distribution information of the lightness value histogram for the air region of the input image; and

when the further judgment result is no, determining the photo environment of the camera apparatus as one of a dawn or dusk lighting condition.

14. The method according to claim 13, wherein, the second ratio is approximately 80%.

15. The method according to claim 13, further comprising:

if the result of the further decision is affirmative, calculating a lightness value histogram for the terrestrial region of the input image;

yet further judging whether a ratio of a number of pixels with lightness values larger than the first lightness value (T1) in the terrestrial region of the input image to the number of all pixels of the terrestrial region in the input image is greater than a third ratio, based on the lightness value histogram for the terrestrial region of the input image; and

when the yet further judgment result is affirmative, determining the photo environment of the camera apparatus as the daytime lighting condition.

16. The method according to claim 15, wherein, the third ratio is approximately 70%.

17. The method according to claim 15, further comprising:

if the yet further judgment result is negative, more further judging whether a ratio of a number of pixels with lightness values less than the second lightness value (T2) in the terrestrial region of the input image to the number of all pixels of the terrestrial region in the input image is greater than a fourth ratio, based on the lightness value histogram for the terrestrial region of the input image; and

when the more further judgment result is affirmative, determining the photo environment of the camera apparatus as a nighttime lighting condition.

18. The method according to claim 17, wherein, the fourth ratio is approximately 80%.

19. The method according to claim 11, further comprising:

obtaining data to determine the lighting condition for the photo environment based on determined lighting conditions of a plurality of images captured.

20. The method according to claim 11, wherein the camera apparatus is mounted on one of a vehicle or a stationary object.