Object Detection Vision Overlay for Existing Machine Cameras

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Industrial machines equipped with typical video cameras lack object detection capabilities, requiring complex updates and increased downtime and costs when upgrading to object detection systems, and struggle to accurately map object detection information onto existing camera feeds.

Innovation Solution

An object detection vision system that combines image data from vision cameras with detection data from separate detect devices, using a controller to transform and display detected objects within the image data, allowing for efficient object detection and classification without necessitating a complete hardware overhaul.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If typical video cameras are replaced with object detection devices, then object detection capability is improved, but device complexity and downtime increase

Engineering Contradiction:
Improveobject detection capabilityVSAvoidsoftware and hardware updates
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system separates object detection functionality from the main video camera by using independent detect devices (such as LIDAR or radar) that operate parallel to the vision cameras. This segmentation allows the detection function to be added without replacing the entire camera system, reducing complexity while maintaining detection capability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The controller is designed to handle multiple data types simultaneously - it processes both image data from vision cameras and detection data from detect devices, then integrates them into a unified display. This multi-functionality allows the system to maintain video capabilities while adding detection capabilities without requiring separate specialized hardware for each function.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Reliability

If object detection devices are integrated into existing vision systems, then object detection capability is improved, but mapping accuracy deteriorates

Engineering Contradiction:
Improveobject detection capabilityVSAvoidobject detection information mapping accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The controller acts as an intermediary that receives data from both vision cameras and detect devices, then performs coordinate transformations to map detection information onto the camera display coordinates. This intermediary processing ensures accurate spatial alignment between objects detected by different sensors and their visual representation on the display.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system transforms detection data by changing coordinate parameters from the detect device's reference frame to the vision camera's display reference frame. This parameter transformation allows accurate mapping of object positions, sizes, and orientations across different sensor coordinate systems while maintaining detection precision.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS12165417B2Object detection vision system
Publication Date: 2024.12.10 CATERPILLAR INC
  • US12165417B2 patent drawing
  • US12165417B2 patent drawing
  • US12165417B2 patent drawing

AI summary

An object detection vision system and methods are disclosed. A method for detecting objects in a vision system of an industrial machine includes receiving image data from one or more vision cameras and receiving detection data from one or more detect devices. The detection data includes one or more detected objects. The method includes combining the detection data and the image data and transforming the detection data in the image data based on one or more objects in the image data. The method also includes displaying an indication of the detected one or more objects in the image data based on the transformed detection data.