Vehicle Camera Object Sizing with Pitch Angle Correction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object detection systems in autonomous vehicles and driver assistance systems face challenges in accurately determining the dimensions of objects, especially when the camera is not horizontal, leading to errors in object recognition and behavior prediction.

Innovation Solution

A method and system for determining the dimension of an object using a vehicle camera, which involves calculating the distance between the camera and the object by accounting for the camera's pitch angle, and using triangle similarities to determine the object's dimension based on the image and camera focal length.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the camera is not horizontal (pitch angle present), then the field of view coverage is improved, but the object dimension measurement accuracy deteriorates

Engineering Contradiction:

Improvecamera orientation flexibilityVSAvoidobject dimension accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent changes the parameter of horizon position in the image to compensate for pitch angle effects. By dynamically adjusting the reference horizon position based on detected pitch angle, the system maintains accurate dimension measurements even when the camera is tilted, thus resolving the contradiction between camera orientation flexibility and measurement accuracy

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces mechanical leveling adjustments with a computational correction method. Instead of physically adjusting the camera to remain horizontal, the system uses image processing and geometric calculations to compensate for the pitch angle, substituting a mechanical constraint with an algorithmic solution

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If simple object detection methods are used, then the system complexity is reduced, but the object dimension determination accuracy deteriorates

Engineering Contradiction:

Improvesystem complexityVSAvoidobject dimension accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent introduces geometric dimensionality by utilizing triangle similarity relationships between the image plane and real world. By establishing proportional relationships across different spatial dimensions (image coordinates to real-world coordinates), the system achieves accurate dimension determination through geometric reasoning rather than complex mechanical or computational approaches

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS20250029400A1A method for determining a dimension of an object

Publication Date: 2025.01.23 AUTOBRAINS TECH LTD

AI summary

A method for calculating a dimension of an object, the method comprises: (a) receiving an image that was acquired by a vehicle camera of a vehicle; the image captures the horizon, the object, and road lane boundaries; (b) determining an initial row-location horizon estimate and a row-location contact point estimate, the row-location contact point estimate represents a contact between the object and a road on which the vehicle is positioned; (c) determining a vehicle camera pitch angle correction and an actual vehicle camera pitch angle, wherein the vehicle camera pitch angle correction, once applied, will cause the road lanes boundaries to be parallel to each other in a real world; (d) calculating the distance between the vehicle and the object based the determined values; and (e) determining the dimension of the object based on the focal length of the vehicle camera, a corresponding dimension of the object within the image and the distance between the vehicle camera and the object.