Controller for a Working Vehicle

• US 20170006261A1
• Filed: 06/30/2016
• Published: 01/05/2017
• Est. Priority Date: 07/03/2015
• Status: Abandoned Application

• Current Assignee: CNH Industrial America LLC (CNH Industrial N.V.)
• Original Assignee: CNH Industrial America LLC (CNH Industrial N.V.)
• Inventors: Houthooft, Rein, Verstichel, Stijn, Debilde, Benoit, Foster, Christopher A.
• Application Number:
  US15/199,090
• Publication Number:
  US 20170006261A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 10/457 by analysing connectivity, e.g. edge linking, connected component analysis or slices
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

A controller configured to receive image data representative of the surroundings of a working vehicle. The image data comprises a plurality of portion data. The controller determines one or more features associated with each of the plurality of portion data. For each of the plurality of portion data, the controller applies a label-attribution-algorithm to attribute one of a plurality of predefined labels to the portion data in question based on: (i) features determined for the portion data in question; and (ii) features determined for proximate portion data, which is portion data that is proximate to the portion data in question. The labels are representative of objects. The controller provides a representation of the attributed labels and their position in the received image data.

Claims

1. A controller configured to:

receive image data representative of the surroundings of a working vehicle, the image data comprising a plurality of portion data;

determine one or more features associated with each of the plurality of portion data;

for each of the plurality of portion data, apply a label-attribution-algorithm to attribute one of a plurality of predefined labels to the each of the plurality of portion data based on;

(i) features determined for the each of the plurality of portion data; and

(ii) features determined for proximate portion data, which is portion data that is proximate to the each of the plurality of portion data; and

provide a representation and position of the labels attributed to the plurality of portion data,

wherein the labels are representative of objects.

2. The controller of claim 1, wherein the working vehicle is an agricultural vehicle, a construction vehicle, or an off-road vehicle.

3. The controller of claim 1, wherein the received image data comprises video data, and wherein the controller is further configured to provide as an output, in real-time, a representation of the plurality of predefined labels and their position in the received video data.

4. The controller of claim 1, further configured to control the working vehicle in accordance with the labels attributed to the plurality of portion data.

5. The controller of claim 4, further configured to set a machine operating parameter of the working vehicle in accordance with the labels attributed to the plurality of portion data.

6. The controller of claim 4, further configured to cause a feedback component to provide feedback to an operator of the working vehicle in accordance with the labels attributed to the plurality of portion data.

7. The controller of claim 1, further configured to apply the label-attribution-algorithm to attribute one of a plurality of predefined labels to the each of the plurality of portion data based on one or more labels associated with the proximate portion data.

8. The controller of claim 1, wherein the label-attribution-algorithm comprises an energy based model.

9. The controller of claim 1, wherein the label-attribution-algorithm is configured to perform semantic object detection.

10. The controller of claim 1, further configured to:

receive training image data and associated user-selected-predetermined-label data; and

apply a machine-learning-algorithm to the label-attribution-algorithm based on the received training image data and user-selected-predetermined-label data, in order to set one or more parameters of the label-attribution-algorithm.

11. The controller of claim 1, wherein the image data comprises pixel data, and the controller is further configured to perform a clustering-algorithm to determine each of the plurality of portion data, wherein each portion data comprises a plurality of neighboring pixel data that satisfy a similarity metric.

12. The controller of claim 1, further configured to provide the representation and position of each of the plurality of predefined labels as an overlay to the received image data.

13. The controller of claim 1, wherein the label-attribution-algorithm is configured to also attribute a confidence level to the labels attributed to the plurality of portion data.

14. The controller of claim 13, wherein the label-attribution-algorithm is configured to:

attribute a secondary predetermined label to one or more of the plurality of portion data, along with a confidence level associated with each secondary label; and

provide a representation of the one or more secondary labels and their position in the received image data.

15. The controller of claim 13, further configured to control the working vehicle in accordance with:

the labels attributed to the plurality of portion data; and

the confidence levels associated with the labels.