Systems and methods for object detection

• US 10,049,434 B2
• Filed: 10/15/2015
• Issued: 08/14/2018
• Est. Priority Date: 10/15/2015
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Mosher, Aaron Y., Kreienheder, Charles Robert
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): Torres, Jose M
• Application Number:
  US14/884,066
• Publication Number:
  US 20170109891A1
• Time in Patent Office: 1,034 Days
• Field of Search: None
• CPC Class Codes: G06T 1/20 Processor architectures; Processor configuration, e.g. pipelining
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20024 Filtering details
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2210/12 Bounding box
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06T 7/90 Determination of colour characteristics

Abstract

A computing device for detecting an object of interest in an image is provided. The computing device includes a memory device and a processor to process image data by evaluating pixel contrast to facilitate detecting an edge transition in an image, by identifying neighboring pixels that are above a predetermined contrast value, which represent a potential object of interest, filtering the pixels based on color information to identify areas where there is a color edge transition, applying a convolution filter mask to yield regions of pixels having a localized concentration of contrast and color changes, applying a threshold filter for identifying those pixel regions having values that are greater than a predetermined threshold value and grouping the identified pixel regions into one or more groups representing an object of interest, and generating an alert to notify an operator that the object of interest in the image has been detected.

Claims

1. A computing device for detecting an object of interest in an image comprising a plurality of pixels, the image being acquired from a vehicle, the computing device comprising:

a memory device; and

a processor communicatively coupled to said memory device and having encoded instructions that, when executed, are configured to process image data for the plurality of pixels in the image acquired onboard the vehicle by;

applying a Laplace transform to respective contrast values of the plurality of pixels to detect edge transitions in the image, the Laplace transform identifying neighboring pixels among the plurality of pixels that are above a predetermined contrast value and thereby represent a potential object of interest;

filtering the plurality of pixels based on color information to identify areas of high contrast where there is a color edge transition;

applying a convolution filter mask to the plurality of pixels to yield a set of regions among the plurality of pixels having localized concentrations of contrast and color changes;

applying a threshold filter to identify a subset of pixel regions having contrast values that are greater than a predetermined threshold value and grouping the identified subset of pixel regions into one or more groups representing an object of interest on a surface of a body of water; and

generating an alert to notify an operator that the object of interest on the surface of a body of water in the image acquired on board the vehicle has been detected, wherein said processor is further configured to output a visual indicia overlaid on a display of the image to notify the operator the object of interest has been detected in the image.

2. The computing device of claim 1, wherein said processor is configured to generate an output including an audible alert to notify the operator that the object of interest has been detected in the image.

3. The computing device of claim 2, further comprising a camera included on an aerial vehicle that acquires the image and a display device communicatively coupled to said processor and configured to display the image and the alert.

4. The computing device of claim 3, wherein said processor is configured to generate a bounding box around the object of interest that is overlaid on the display of the image to notify the operator of the location of the object of interest in the image.

5. The computing device of claim 1, wherein said processor comprises a general purpose graphics processing unit (GPGPU) and a central processing unit (CPU) that functioning as coprocessors to process image data.

6. The computing device of claim 1, wherein the threshold filter is configured to be adjustably tuned to set a sensitivity for detecting objects of interest.

7. A method for identifying an object of interest in an image comprising a plurality of pixels, the image being acquired from a vehicle, the method comprising:

applying, using a computing device, a Laplace transform to respective contrast values of the plurality of pixels in the image acquired onboard the vehicle to detect edge transitions in the image, the Laplace transform identifying neighboring pixels among the plurality of pixels that are above a predetermined contrast value and thereby represent a potential object of interest;

filtering, using the computing device, the plurality of pixels based on color information to identify areas of high contrast where there is a color edge transition;

applying, using the computing device, a convolution filter mask to the plurality of pixels to yield a set of regions among the plurality of pixels having localized concentrations of contrast and color changes;

applying, using the computing device, a threshold filter to identify a subset of pixel regions having contrast values that are greater than a predetermined threshold value and grouping the identified subset of pixel regions into one or more groups representing an object of interest on a surface of a body of water; and

generating, using the computing device, an alert to notify an operator that the object of interest on the surface of a body of water in the image acquired on board the vehicle has been detected, and outputting a visual indicia overlaid on a display of the image to notify the operator the object of interest has been detected in the image.

8. The method of claim 7, wherein generating an alert comprises generating an audible alert to notify the operator that the object of interest in the image has been detected, wherein the image depicts a surface of a body of water.

9. The method of claim 7, further comprising generating a bounding box around the object of interest that is overlaid on a display of the image to notify the operator of the location of the object of interest in the image.

10. The method of claim 7, further comprising tuning the threshold filter to set a sensitivity for detecting objects of interest.

11. The method of claim 7 wherein evaluating, using a computing device, pixel contrast comprises evaluating using a computing device that includes a general purpose graphics processing unit (GPGPU) and a central processing unit (CPU) that functioning as coprocessors.

12. The method of claim 7, further comprising:

identifying a horizon in the image; and

ignoring pixel data above the horizon or below the horizon.

13. A system for detecting an object of interest in an image, the system comprising:

a camera disposed onboard a vehicle and configured to acquire an image comprising a plurality of pixels; and

a computing device communicatively coupled to said camera and configured to;

applying a Laplace transform to respective contrast values of the plurality of pixels to detect edge transitions in the image, the Laplace transform identifying neighboring pixels among the plurality of pixels that are above a predetermined contrast value and thereby represent a potential object of interest;

filter the plurality of pixels based on color information to identify areas of high contrast where there is a color edge transition;

apply a convolution filter mask to the plurality of pixels to yield a set of regions among the plurality of pixels having localized concentrations of contrast and color changes;

apply a threshold filter to identify a subset of pixel regions having contrast values that are greater than a predetermined threshold value and grouping the identified subset of pixel regions into one or more groups representing an object of interest on a surface of a body of water; and

generate an alert to notify an operator that the object of interest on the surface of the body of water in the image acquired by the camera has been detected, the alert including a visual indicia generated by said computing device and overlaid on a display of the image to notify the operator.

14. The system of claim 13, wherein said camera and said computing device are installed on an unmanned vehicle.

15. The system of claim 13, wherein said computing device is configured to generate a bounding box around the object of interest, the bounding box overlaid on the display of the image to notify the operator of the location of the object of interest in the image.

16. The system of claim 13, wherein said computing device is configured to generate an output including an audible alert to notify the operator that the object of interest has been detected in the image.