CPC E02F 9/267 (2013.01) [B60Q 9/00 (2013.01); G06T 7/001 (2013.01); G06T 7/11 (2017.01); G06T 7/174 (2017.01); G06T 7/70 (2017.01); G06V 20/41 (2022.01); G08B 21/18 (2013.01); E02F 3/32 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/30164 (2013.01)] | 20 Claims |
1. A method comprising:
receiving from a camera associated with a work machine, a video stream including a plurality of images of a bucket of the work machine, the bucket having a model number and at least one ground engaging tool (GET);
based on the model number, selecting:
a matching bucket-tool template corresponding to the bucket from a plurality of bucket-tool templates stored in a template library of the work machine,
a predetermined moment in a dig-dump cycle of the work machine, and
a predetermined position of the bucket during the predetermined moment in the dig-dump cycle;
identifying a plurality of tool images from the video stream over a period of time that matches one or more stored images from the matching bucket-tool template, the plurality of tool images capturing the bucket at the predetermined position during the predetermined moment in the dig-dump cycle and depicting the at least one GET at a plurality of time instances over the period of time;
determining a plurality of tool pixel counts from the plurality of tool images based at least in part on a shape and style of the GET, the plurality of tool pixel counts indicating at least one of:
an area of the GET,
a height of the GET,
a width of the GET, or
a sum of the height and the width of the GET; and
determining a wear level or loss for the at least one GET based on the plurality of tool pixel counts.
|