Trailer Angle Estimation Using Projective Geometry and Visual Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Tow vehicle drivers face challenges in maneuvering trailers due to confusion about steering angles, which can lead to jack-knifing and loss of course, and existing systems are costly and complex.
Innovation Solution
A system using a camera-mounted vehicle controller that determines trailer angles via projective geometry, tracking visual features from images to calculate the trailer angle and transmit it to vehicle systems, utilizing sensors for straight-line detection and projective transformations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a camera-based system with projective geometry is used to determine trailer angles, then device complexity and hardware requirements are reduced, but measurement precision may be affected compared to multi-sensor systems
Solution Approach 1:
The patent replaces complex mechanical sensor systems (multiple cameras, LIDAR, radar) with a simplified camera-based projective geometry system. A single camera captures images of the trailer, and computational projective geometry algorithms process these images to calculate trailer angle, eliminating the need for expensive multi-sensor hardware while maintaining functional capability
Solution Approach 2:
The system creates a virtual 3D model of the trailer and its spatial relationship to the vehicle by projecting 2D camera images into 3D space using projective geometry. This virtual copy allows accurate angle determination without physical contact sensors or complex mechanical measurement devices attached to the trailer
2Ease of operation
If visual feature tracking is used to calculate trailer angles during movement, then ease of operation is improved, but reliability may be affected by image quality and feature detectability
Solution Approach 1:
The system performs preliminary detection of visual features on the trailer before movement begins or during steady-state conditions. These pre-identified features serve as reference points that are tracked throughout subsequent maneuvers, ensuring consistent angle calculation even during dynamic movement when image quality may vary
Solution Approach 2:
The system continuously tracks visual features across multiple frames and uses feedback from previous position estimates to refine current angle calculations. This temporal feedback mechanism maintains reliability during movement by comparing expected feature positions with actual detected positions and adjusting calculations accordingly
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
A method for determining a trailer angle between a tow vehicle and a trailer attached to the tow vehicle includes receiving images from a camera positioned on a rear portion of the tow vehicle with a data processing hardware device, determining visual features from the images, tracking the visual features while the tow vehicle and trailer are moving and calculating, at the data processing hardware, the trailer angle based on the visual features. The trailer angle is then transmitted from the data processing hardware to one or more vehicle systems.