VISION-BASED SCENE DETECTION

• US 20130128044A1
• Filed: 11/17/2011
• Published: 05/23/2013
• Est. Priority Date: 11/17/2011
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Zhang, Wende, Wang, Jinsong
• Granted Patent: US 9,635,271 B2
• Time in Patent Office: Days
• US Class Current: 348/148
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/00 Image analysis
• CPC Class Codes: H04N 23/71 Circuitry for evaluating the brightness variation

Abstract

A method of distinguishing between daytime lighting conditions and nighttime lighting conditions based on a captured image by a vision-based imaging device along a path of travel. An image is captured by a vision-based imaging device. A region of interest is selected in the captured image. A light intensity value is determined for each pixel within the region of interest. A cumulative histogram is generated based on light intensity values within the region of interest. The cumulative histogram including a plurality of category bins representing the light intensity values. Each category bin identifies an aggregate value of light intensity values assigned to each respective category bin. An aggregate value is compared within a predetermined category bin of the histogram to a first predetermined threshold. A determination is made whether the image is captured during the daytime lighting conditions as a function of the aggregate value within the predetermined category bin.

Claims

1. A method of distinguishing between daytime lighting conditions and nighttime lighting conditions based on a captured image by a vision-based imaging device along a path of travel, the method comprising the steps of:

capturing an image by a vision-based imaging device;

selecting a region of interest in the captured image;

determining a light intensity value for each pixel within the region of interest;

generating a cumulative histogram based on light intensity values within the region of interest, the cumulative histogram including a plurality of category bins representing the light intensity values, each category bin identifying an aggregate value of light intensity values assigned to each respective category bin;

comparing an aggregate value within a predetermined category bin of the histogram to a first predetermined threshold; and

determining whether the image is captured during the daytime lighting conditions as a function of the aggregate value within the predetermined category bin.

2. The method of claim 1 wherein the determination that the image is captured during the daylight lighting conditions is based on the aggregate number being less than a first predetermined threshold.

3. The method of claim 2 wherein the determination of whether the captured image is obtained during the daytime lighting conditions further comprises the step of determining whether the captured image includes a daylight blocking structure over the path of travel.

4. The method of claim 3 wherein determining whether the captured image includes a daylight blocking structure over the path of travel comprises:

comparing an aggregate value of the light intensity values within the second predetermined category bin of the cumulative histogram to a second predetermined threshold;

determining whether the aggregate value of the light intensity values within the second predetermined category bin is greater than the second predetermined threshold; and

determining that the captured image includes the daylight blocking structure over the path of travel in response to the aggregate value within the second predetermined category bin being greater than the predetermined threshold.

5. The method of claim 4 wherein the determination that the captured image includes the daylight blocking structure over the path of travel is output to a global positioning system, wherein the global positioning system estimates a time when a loss of signal occurs in the global positioning system as a result of vehicle traveling under the daylight blocking structure.

6. The method of claim 3 wherein the daylight blocking structure over the path of travel includes a tunnel over the path of travel.

7. The method of claim 3 wherein the daylight blocking structure over the path of travel includes a bridge over the path of travel.

8. The method of claim 1 wherein a determination that the captured image is obtained during the nighttime lighting conditions is based on the aggregate number being greater than the first predetermined threshold.

9. The method of claim 8 wherein determining that the capture image is obtained during nighttime lighting conditions further comprises the step of determining whether the nighttime lighting conditions include substantial lighting for illumination the path of travel in response to the aggregate value being greater than the first predetermined threshold, wherein determining an illumination of the path of travel comprises:

comparing an aggregate value of a second predetermined category bin of the cumulative histogram to a third predetermined threshold;

determining whether an aggregate value of the light intensity values within the second predetermined category bin is less than the third predetermined threshold; and

determining that the captured image includes the path of travel in the captured image is substantially illuminated in response to the second predetermined category being less than the third predetermined threshold.

10. The method of claim 1 wherein the determined daytime and nighttime lighting conditions is output to a vehicle-based module that enables vehicle operations based on environment light sensing.

11. The method of claim 10 wherein the vehicle-based module includes auto headlamps wherein the output is used to enable auto headlamps.

12. The method of claim 10 wherein the vehicle-based module includes a vehicle vision system, and wherein output is used to modify the vehicle vision system.

13. The method of claim 1 wherein the selected region of interest represents an expected location of a skyline within the captured image.

14. The method of claim 1 wherein capturing an image by a vision-based imaging device includes capturing multiple images over a period of time, wherein the multiple images are cumulatively analyzed for detecting the daytime lighting conditions.

15. The method of claim 14 wherein the multiple images are used to determine a transitioning region in a road of travel between an unobstructed daylight portion of the road of travel and an obstructed daylight portion of the road of travel.

16. The method of claim 1 wherein a training phase is used to identify which of the respective category bins of the cumulative histogram are selected as the predetermined category bin and a second predetermined category bin, wherein the training phase comprises:

capturing a plurality of images of various lighting conditions;

selecting a region of interest for each captured image;

determining a light intensity value for each pixel within the region of interest for each captured image;

generating a cumulative histogram for each image based on the light intensity values within the region of interest, each cumulative histogram including a plurality category bins representing the light intensity values, each category bin identified by a comparative factor that is derived as function of the light intensity values assigned to each respective category bin;

identifying a first category bin from the plurality of histograms that distinguishes a daytime lighting condition from a nighttime lighting condition based on comparative factors, the first category bin being selected as the predetermined category bin;

identifying a second category bin from the plurality of histograms that distinguishes a daytime lighting condition having a daylight blocking structure from an unobstructed daytime lighting condition based on the comparative factors, the second category bin being selected as the second predetermined category bin.

17. The method of claim 16 wherein the predetermined category bin is determined by identifying a largest difference between a comparative factor of a respective category bin of a histogram associated with a daytime lighting condition and a comparative factor of a correlating category bin of a histogram associated with the nighttime lighting condition.

18. The method of claim 17 wherein the second predetermined category bin is determined by identifying a largest difference between a comparative factor of a respective category bin of a histogram associated with an unobstructed daylight condition and a comparative factor of a correlating category bin of a histogram associated with the unobstructed daylight condition.

19. The method of claim 16 wherein the predetermined category bin and the second predetermined category bin are selected using a feature selection technique.

20. The method of claim 16 wherein the comparative value is an aggregate value of the light intensity values within a respective category bin.