Trailer Coupler Tracking Using Vehicle Motion Data Fusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing visual object tracking systems for tow vehicles face challenges in maintaining accurate object tracking when camera motion occurs, leading to potential loss of the trailer coupler's location in future images, especially when the tow vehicle is autonomously maneuvering in a rearward direction.

Innovation Solution

The system employs data processing hardware that receives images from a rear camera and combines them with vehicle sensor data, including steering wheel angle sensors, wheel encoders, and GPS, to determine the trailer coupler's position and update it based on vehicle motion, using algorithms like coupler point tracking, low-speed motion estimation, and image point motion modules to predict the coupler's location in future images, ensuring accurate tracking and autonomous maneuvering.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If visual object tracking is performed using only image data without considering camera motion, then the tracking system is simple to implement, but the tracking accuracy is lost when camera motion occurs

Engineering Contradiction:
Improvetracking accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces vehicle motion data from sensors (accelerometers, gyroscopes, wheel encoders) as an intermediary element to bridge the gap between image data and actual object position. This mediator compensates for camera motion effects by providing independent motion information that is then integrated with image tracking data to maintain accurate coupler positioning despite camera movement

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system merges multiple data sources including image processing data from the coupler tracker and vehicle motion data from sensors into a unified tracking solution. By combining these independent data streams through data fusion algorithms, the system achieves robust tracking accuracy that compensates for the limitations of each individual data source while managing complexity through modular integration

Inventive Principle:
Principle #5Merging (Combining)

2Extent of automation

If the tow vehicle maneuvers autonomously in rearward direction, then the hitching operation is automated, but the trailer coupler may be lost in future images due to camera motion

Engineering Contradiction:
Improveautonomous maneuveringVSAvoidobject tracking reliability
Core Design Contradiction:
Extent of automationVSReliability

Solution Approach 1:

The system implements continuous feedback loops where vehicle motion sensors provide real-time motion data that feeds back to the tracking algorithm. This feedback mechanism allows the system to dynamically adjust for camera motion effects during autonomous maneuvers, predicting where the coupler should appear in subsequent frames based on measured vehicle acceleration, angular velocity, and wheel encoder data

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The tracking system performs preliminary compensation for expected camera motion by using vehicle motion data to predict coupler position in future images before the actual image capture occurs. This preliminary action allows the system to pre-adjust tracking parameters and maintain readiness to accurately locate the coupler even during rapid autonomous maneuvers

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3790745B1Visual object tracker
Publication Date: 2023.08.02 CONTINENTAL AUTONOMOUS MOBILITY US LLC
  • EP3790745B1 patent drawingFigure 1
  • EP3790745B1 patent drawingFigure 2
  • EP3790745B1 patent drawingFigure 3

AI summary

A method for tracking a trailer coupler (212) positioned behind a tow vehicle (100) is provided. The method includes receiving one or more images (143) from a camera (142) positioned on a back portion of the tow vehicle (100). The method also includes determining a trailer coupler position within the one or more images. The trailer coupler position associated with the trailer coupler (212). Additionally, the method includes receiving vehicle sensor data (141) from one or more vehicle sensors. The method includes determining vehicle motion data based on the received vehicle sensor data (141). The method also includes determining an updated coupler position based on the trailer coupler position and the vehicle motion data.