Trailer Hitch Angle Detection via Rotated Template Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Reversing a vehicle while towing a trailer can be challenging due to the reliance on accurate hitch angle measurements, which are often unreliable in existing systems, especially for infrequent users or those with various types of trailers.

Innovation Solution

A trailer backup assist system that uses an imaging device to capture images and a controller to process them, deriving a template image and rotating it to match with search images at candidate hitch point locations, assigning confidence scores to determine the hitch angle, thereby improving hitch angle detection accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional hitch angle measurement systems are used, then the system complexity is reduced, but the measurement precision and reliability deteriorate

Engineering Contradiction:
Improvehitch angle measurement precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical hitch angle sensors with an optical image processing system. The controller captures images using an imaging device, processes these images to identify the trailer and hitch point, and calculates the hitch angle through image analysis rather than mechanical measurement, thereby improving reliability while managing complexity through software-based solutions

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an imaging device as an intermediary between the physical hitch angle and the measurement system. Instead of directly measuring the mechanical angle, the system captures visual information of the trailer and hitch point, processes this intermediate visual data, and derives the hitch angle from the image characteristics, enabling more reliable measurements

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If multiple candidate hitch point locations are evaluated, then the reliability of hitch point identification is improved, but the processing time increases

Engineering Contradiction:
Improvehitch point identification reliabilityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-identifying multiple candidate hitch point locations based on trailer geometry and image features before final hitch point selection. The system evaluates several potential locations using confidence scores and selects the most reliable one, thereby improving identification reliability while managing processing time through pre-computation of candidate positions

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent evaluates multiple candidate hitch point locations (excessive action) rather than relying on a single identification method. By assessing several candidates and selecting the best match based on confidence scores, the system ensures reliable hitch point identification even though this requires processing more data than a single-point approach would demand

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS9798953B2Template matching solution for locating trailer hitch point
Publication Date: 2017.10.24 FORD GLOBAL TECH LLC
  • US9798953B2 patent drawing
  • US9798953B2 patent drawing
  • US9798953B2 patent drawing

AI summary

A system for detecting a hitch angle between a vehicle and a trailer is provided herein. An imaging device is configured to capture images of the trailer and a controller is configured to process images captured by the imaging device. The controller derives a template image and rotates the template image relative to a search image about an imaged hitch point that is common to the template image and the search image. The location of the imaged hitch point corresponds to a selected one of a number of candidate hitch point locations. The hitch angle is determined based on an angle at which the template image is rotated relative to the search image to generate a match therebetween.