Granted Patent B1

US 9,767,370 · App. 15/215,890 · Granted Sep 19, 2017

Abstract

Claims (44)

1. A method of identifying potential construction objects from images, the method comprising:

receiving, by one or more computing devices having one or more processors, an image captured by a camera associated with a vehicle as the vehicle is driven along a roadway;

converting, by the one or more computing devices, the image into a first channel corresponding to an average brightness contribution from red, blue and green channels of the image;

converting, by the one or more computing devices, the image into a second channel corresponding to a contribution of a color from the red and the green channels of the image; and

using, by the one or more computing devices, a first template moving in a sliding window pattern over the image to identify a region of the image from the first channel and the second channel,

wherein the first template includes a first area and identifying the region further includes determining from the first channel that image data within the first area of the first template corresponding to the region meets a brightness threshold value such that the region is identified as a potential construction object and

wherein the first area is a first inner area that is situated within a second middle area of the first template that is situated within a third outer area of the first template and identifying the region further includes determining from the second channel whether a difference in image data values between the first inner area and the third outer area meets a threshold color value.

2. The method of claim 1 , further comprising:

using a classifier to determine whether the region includes a stripe; and

identifying the potential construction object as a construction object based on the determination of whether the region includes a stripe.

3. The method of claim 1 , wherein the first inner area, second middle area, and third outer area are rectangular.

4. The method of claim 1 , further comprising using a second template including an inner area, a middle area, and an outer area that are each rectangular to identify the region, wherein the second template and first template are different sizes, and a ratio of sizes of the inner area of the second template, the middle area of the second template, and the outer area of the second template is a ratio of sizes of the first inner area, second middle area and third outer area of the first template.

5. The method of claim 1 , wherein the contribution of color corresponds to at least one of yellow, orange, and red.

6. The method of claim 1 , further comprising, after identifying the region, controlling the vehicle based on the potential construction object.

7. A system of identifying potential construction objects from images, the system comprising one or more computing devices having one or more processors configured to:

receive an image captured by a camera associated with a vehicle as the vehicle is driven along a roadway;

convert the image into a first channel corresponding to an average brightness contribution from red, blue and green channels of the image;

convert the image into a second channel corresponding to a contribution of a color from the red and the green channels of the image; and

use a first template moving in a sliding window pattern to identify a region of the image from the first channel and the second channel,

wherein the first template includes a first area and identifying the region further includes determining from the first channel that image data within the first area of the first template corresponding to the region meets a brightness threshold value such that the region is identified as a potential construction object and

wherein the first area is a first inner area that is situated within a second middle area of the first template that is situated within a third outer area of the first template and identifying the region further includes determining from the second channel whether a difference in image data values between the first inner area and the third outer area meets a threshold color value.

8. The system of claim 7 , wherein the one or more processors are further configured to:

using a classifier to determine whether the region includes a stripe; and

identifying the potential construction object as a construction object based on the determination of whether the region includes a stripe.

9. The system of claim 7 , wherein the first inner area, second middle area, and third outer area are rectangular.

10. The system of claim 7 , wherein the one or more processors are further configured to use a second template including an inner area, a middle area, and an outer area that are each rectangular to identify the region, wherein the second template and first template are different sizes, and a ratio of sizes of the inner area of the second template, the middle area of the second template, and the outer area of the second template is a ratio of sizes of the first inner area, second middle area and third outer area of the first template.

11. The system of claim 7 , wherein the contribution of color corresponds to at least one of yellow, orange, and red.

12. The system of claim 7 , further comprising, after identifying the region, controlling the vehicle based on the potential construction object.

13. A non-transitory, computer readable medium on which instructions are stored, the instructions, when executed by one or more processors cause the one or more processors to perform a method of identifying potential construction objects from images, the method comprising:

receiving an image captured by a camera associated with a vehicle as the vehicle is driven along a roadway;

converting the image into a first channel corresponding to an average brightness contribution from red, blue and green channels of the image;

converting the image into a second channel corresponding to a contribution of a color from the red and the green channels of the image; and

using a first template moving in a sliding window pattern over the image to identify a region of the image from the first channel and the second channel,

wherein the first template includes a first area and identifying the region further includes determining from the first channel that image data within the first area of the first template corresponding to the region meets a brightness threshold value such that the region is identified as a potential construction object and

wherein the first area is a first inner area that is situated within a second middle area of the first template that is situated within a third outer area of the first template and identifying the region further includes determining from the second channel whether a difference in image data values between the first inner area and the third outer area meets a threshold color value.

14. The medium of claim 13 , wherein the method further comprises using a second template including an inner area, a middle area, and an outer area that are each rectangular to identify the region, wherein the second template and first template are different sizes, and a ratio of sizes of the inner area of the second template, the middle area of the second template, and the outer area of the second template is a ratio of sizes of the first inner area, second middle area and third outer area of the first template.

15. The method of claim 2 , wherein the classifier detects edges of the stripe.

16. The system of claim 8 , wherein the classifier detects edges of the stripe.

17. The medium of claim 13 , wherein the one or more processors are further configured to:

using a classifier to determine whether the region includes a stripe; and

identifying the potential construction object as a construction object based on the determination of whether the region includes a stripe.

18. The medium of claim 17 , wherein the classifier detects edges of the stripe.

19. The medium of claim 13 , wherein the first inner area, second middle area, and third outer area are rectangular.

20. The medium of claim 13 , wherein the contribution of color corresponds to at least one of yellow, orange, and red.

Assignments (6)