SYSTEM FOR EVALUATING AGRICULTURAL MATERIAL

• US 20170112057A1
• Filed: 08/31/2016
• Published: 04/27/2017
• Est. Priority Date: 10/23/2015
• Status: Active Grant

• Current Assignee: Carnegie Mellon University, Deere & Company
• Original Assignee: Carnegie Mellon University, Deere & Company
• Inventors: Loukili, Tarik, Pazzementi, Zach Abraham, Hageman, John M.
• Granted Patent: US 10,188,036 B2
• Time in Patent Office: Days
• CPC Class Codes: A01D 41/06 Combines with headers
• CPC Class Codes: A01D 41/127 Control or measuring arrangements specially adapted for combines
• CPC Class Codes: A01D 41/1277 for measuring grain quality
• CPC Class Codes: A01D 61/00 Elevators or conveyors for binders or combines
• CPC Class Codes: A01F 12/46 Mechanical grain conveyors
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30188 Vegetation; Agriculture
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

Disclosed herein is a diagnostic module configured to determine an average image of a set or a sequence of collected images, to obtain a last image of the set or the sequence of collected images, and to determine a difference between the average image and the last image to yield a differenced image. Background image data or background pixels are eliminated from the differenced image to produce an initial image mask of unchanged content in the last image. A diagnostic module or data processor determines a mask area of the initial image mask or a revised image mask derived from the initial image mask. A diagnostic module or data processor generates an alert data message to inspect or clean the imaging system if the mask area exceeds a threshold area.

Claims

1. A method for evaluating performance of an imaging system, the method comprising:

collecting a set of images that relate to agricultural material in a passage;

determining an average image of the set of collected images;

identifying a last image in the set of collected images;

determining a difference between the average image and the last image to yield a differenced image;

eliminating background image data from the differenced image to produce an initial image mask of unchanged content in the last image;

determining a mask area of the initial image mask; and

generating an alert data message to inspect the imaging system if the mask area exceeds a threshold area.

2. The method according to claim 1 wherein collecting the set of images comprises:

collecting a plurality of images that relate to the agricultural material, and

storing the plurality of images in a data storage device.

3. The method according to claim 1 further comprising:

performing a logical operation on a set of initial image masks to produce a revised image mask.

4. The method according to claim 3 wherein performing the logical operation comprises applying a logical conjunction operation to the set of initial image masks.

5. The method according to claim 1 wherein eliminating background image data from the differenced image comprises applying color differentiation to identify and eliminate background pixels of color or hue that are associated with an interior of the passage that is observable by the imaging system.

6. The method according to claim 1 wherein determining the average image comprises determining a mean, median, or mode corresponding to individual pixels occupying a same position in successive images in the set of images to facilitate identification of unchanged content in the set of images.

7. The method according to claim 6 wherein the unchanged content is identified by determining of the average image and eliminating background image data,

wherein the unchanged content is indicative of agricultural material or foreign material that is stuck to a window or lens of the imaging system, or foreign material or agricultural material that is blocking or clogging the passage associated with the imaging system.

8. The method according to claim 1 further comprising:

sending an alert data message to a user interface, wherein the alert data message prompts a user to inspect the imaging system.

9. The method according to claim 3 wherein determining a mask area comprises determining a mask area of the revised image mask.

10. A system for evaluating performance of an imaging system, the system comprising:

an imaging device for collecting a set of images that relate to agricultural material in a passage;

a controller coupled to the imaging device, the controller comprising;

a data port for receiving the set of images from the imaging device,

a diagnostic module comprising instructions stored on a data storage device,

an electronic data processor arranged to execute the instructions associated with the diagnostic module,

wherein execution of the diagnostic module causes the controller to perform a method comprising;

determining an average image of the set of images;

obtaining a last image of the set of images;

determining a difference between the average image and the last image to create a differenced image;

eliminating background image data from the differenced image to produce an initial image mask of unchanged content identified in the last image;

determining a mask area of the initial image mask; and

generating an alert data message to inspect the imaging system if the mask area exceeds a threshold area.

11. The system according to claim 10, wherein the data storage device comprises:

a buffer memory for storing the set of images, wherein the electronic data processor executes the instructions associated with the diagnostic module when the buffer memory is full.

12. The system according to claim 10, wherein the diagnostic module further comprises instructions that cause the data processor to perform a logical operation on a set of initial image masks to produce a revised image mask.

13. The system according to claim 12 wherein the logical operation comprises applying a logical conjunction operation to the set of initial image masks to produce the revised image mask.

14. The system according to claim 10, wherein the diagnostic module further comprises instructions that cause the data processor, when eliminating the background image data, to apply color differentiation to identify and eliminate the background pixels of color or hue that are associated with an interior of the passage that is observable by the imaging system.

15. The system according to claim 10, wherein the diagnostic module further comprises instructions that cause the data processor, when determining the average image, to determine a mean, median, or mode corresponding to individual pixels occupying a same position in successive images in the set of images to facilitate identification of unchanged content in the set of images.

16. The system according to claim 15 wherein the diagnostic module further comprises instructions that cause the data processor to identify the unchanged content, wherein the unchanged content is indicative of agricultural material or foreign material that is stuck to a window or lens of the imaging system, or foreign material or agricultural material that is blocking or clogging the passage in a harvesting machine associated with the imaging system.

17. The system according to claim 10, wherein the diagnostic module further comprises instructions that cause the data processor to send the alert data message to a user interface.