Bucket GET Wear Detection Using Video Pixel Counts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wear detection systems for ground engaging tools (GET) rely on computationally expensive neural networks and machine learning, which can lead to false positives and inefficiencies, especially when processing large video streams.
Innovation Solution
A method and system using computer vision techniques to detect wear or loss of GET by analyzing video streams from a camera associated with a work machine, identifying tool images, determining pixel counts, and calculating wear levels based on pixel count changes over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If neural networks and machine learning are used for wear detection, then detection capability is improved, but computational cost increases and false positives increase
Solution Approach 1:
The patent extracts only the essential feature for wear detection - the number of pixels representing the GET in each image - rather than using comprehensive machine learning analysis. This extraction approach reduces computational complexity while maintaining detection effectiveness by focusing solely on the critical measurement parameter.
Solution Approach 2:
The patent replaces expensive, computationally intensive neural networks with a simple, low-cost pixel counting method. This substitution uses minimal processing resources and can be executed efficiently on standard hardware, eliminating the need for complex trained models while achieving the same wear detection objective.
2Measurement precision
If neural networks and machine learning are used for wear detection, then detection capability is improved, but false positives increase
Solution Approach 1:
By extracting only the pixel count of the GET from each image and comparing it to previous measurements, the system eliminates the complexity of machine learning decision boundaries that can lead to false positives. This simple extraction and comparison approach is more reliable because it directly measures the physical quantity of interest without intermediate processing steps that could introduce errors.
Solution Approach 2:
The patent creates a simple numerical copy (pixel count) of the GET from each image and compares this copy to previous copies to determine wear. This copying approach avoids the complexity of machine learning models that may misinterpret image features, providing a more reliable and interpretable measurement that directly reflects the physical state of the GET.
3Measurement precision
If video streams are processed using machine learning, then wear detection capability is improved, but processing time increases
Solution Approach 1:
The patent extracts only the essential information (GET pixel count) from each video frame using simple image processing operations, avoiding time-consuming machine learning inference. This extraction method processes each frame in minimal time while maintaining the ability to track wear progression across the video sequence.
Solution Approach 2:
The patent replaces time-consuming machine learning processing with a lightweight pixel counting operation that can be executed rapidly on each video frame. This substitution enables real-time or near-real-time wear monitoring from video streams using standard processing hardware without the computational burden of trained neural networks.
Data Source
AI summary
A wear detection system can be configured to receive a video stream including a plurality of images of a bucket of the work machine from a camera associated with the work machine. The bucket has one or more ground engaging tools (GET). The wear detection system can also be configured to identify a plurality of tool images from the video stream over a period of time. The plurality of tool images depict the GET at a plurality of instances over a period of time. The wear detection system can also be configured to determine a plurality of tool pixel counts from the plurality of tool image and determine a wear level for the GET based on the plurality of tool pixel counts.