Caterpillar Inc.

Nolan S Finch

John Michael Plouzek

Praveen Halepatali

Timothy J Bennett

Yue Wang

Mitchell Chase Vlaminck

Lingyu Ma

Kook In Han

Daniel A Smyth

David Conway Atkinson

Christopher Ha

Qi Wang

Yihong Yang

Zachary Smith

Neil Moloney

Sang Kyum Kim

Meng Han

Vineet Agarwal

A method for determining an angle of a tip of a ripper shank includes a controller receiving an input command. The controller estimates an angle of the tip based on one or more parameters of the input command. Further, the controller acquires a video feed of the ripper shank and detects an object in the video feed. The controller identifies the object as one of the ripper shank or a component movable with a movement of the ripper shank based on a match of a color of the object to a predefined color and a match of a profile of the object to a predefined profile. The controller co-relates the profile to an angular value in a map table and sets the angular value to be an actual angle of the tip over the angle of the tip estimated based on the input command.

Method for determining angle of tips of ripper shanks in dozer machines

An ECU includes a memory including computer executable instructions for monitoring the condition of a ground engaging tool, and a processor coupled to the memory and configured to execute the computer executable instructions, the computer executable instructions when executed by the processor cause the processor to: acquire an image of the ground engaging tool, evaluate the image using an algorithm that compares the acquired image to a database of existing images to determine the damage, the amount of wear, or the absence of the ground engaging tool, and grade the quality of the acquired image.

Bucket get monitoring system

The electronic control unit includes a memory including computer executable instructions for recognizing a ground engaging tool; and a processor coupled to the memory and configured to execute the computer executable instructions, the computer executable instructions when executed by the processor cause the processor to: determine a dimension of a ground engaging tool installed on a work tool; compare the determined dimension of the ground engaging tool installed on a work tool to the theoretical dimension of a new ground engaging tool installed on the work tool; and calculate the difference between the determined dimension and the theoretical dimension.

Ground engaging tool monitoring system

A device is disclosed. The device may obtain a machine model of a machine and associated motion data for the machine model of the machine. The device may render the machine model into a rendered environment associated with a set of characteristics. The device may capture a set of images of the machine model and the rendered environment based on rendering the machine model into the rendered environment. The device may determine bounding box data for the set of images of the machine model and the rendered environment based on the position of the machine model within the rendered environment relative to an image capture orientation within the rendered environment. The device may provide the set of images of the machine model and the rendered environment and the bounding box data as a data set for object detection.

Artificial image generation for training an object detection system

A device for measuring wear is disclosed. The device may receive images associated with a component, and may receive a three-dimensional (3D) model of the component. The device may generate an image point cloud based on the images, and may generate a model point cloud based on the 3D model of the component. The device may perform a first alignment of the image point cloud and the model point cloud to generate first-aligned point clouds, and may perform a second alignment of the first-aligned point clouds to generate second-aligned point clouds. The device may generate 3D mask regions based on the second-aligned point clouds, and may project the 3D mask regions on the images. The device may process the 3D mask regions, projected on the images, to determine reference points in the images, and may determine an amount of wear associated with the component based on the reference points.

Measurement platform that automatically determines wear of machine components based on images

A method for tracking workers at a worksite is disclosed. The method includes acquiring a video of the worksite and detecting a movement of objects in the video. Each object is represented by a plurality of pixels. The method includes identifying an item associated with at least one object by clustering a set of pixels of the plurality of pixels based on a color of the set of pixels. Next, the method includes determining the item as a hard hat based on at least a shape of the set of pixels, and identifying the object as a specific worker based on the color of the set of pixels. The method also includes generating a movement data associated with the specific worker based on a tracking of the hard hat.

Method and system for tracking workers at worksites

A machine behavior classification system may include an electronic data collection system and an electronic data analysis system. The electronic data collection system may have an image capture apparatus that is configured to monitor a machine and the image capture apparatus may produce an image data file of the machine. Moreover, the electronic data analysis system may receive the image data file and may perform a data analysis of the image data file.

Machine onboard activity and behavior classification

A wear measurement system for a component is disclosed. The wear measurement system may include an imaging device configured to obtain a plurality of two-dimensional images of the component. The wear measurement system may also include a controller. The controller may be configured to generate a three-dimensional point cloud representing the component based on the two-dimensional images. The controller may also be configured to overlay a computer model of the component on the three-dimensional point cloud. Further, the controller may be configured to project the computer model on the two-dimensional images. The controller may also be configured to select at least two reference points appearing in each of a subset of images selected from the two-dimensional images. The controller may be configured to determine locations of the two reference points in the three-dimensional point cloud, determine an image distance between the locations, and determine an amount of wear based on the image distance.

Wear measurement system using a computer model

A wear measurement system for a component is disclosed. The wear measurement system may have an imaging device configured to obtain a plurality of two-dimensional images of the component. The wear measurement system may also have a controller. The controller may be configured to generate a three-dimensional point cloud representing the component based on the two-dimensional images. The controller may also be configured to select at least two reference points appearing in each of a subset of images selected from the two-dimensional images. Further, the controller may be configured to determine locations of the two reference points in the three-dimensional point cloud. The controller may also be configured to determine an image distance between the locations. In addition, the controller may be configured to determine an amount of wear based on the image distance.

Growing community of inventors

Champaign, IL, United States of America

Nolan S Finch