Stereo Reference Surface Detection for Accurate Mobile Dimensioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy of surface detection from stereo images is negatively affected under certain conditions, leading to inaccurate dimensioning of objects, particularly due to low point cloud density and miscalibration of motion sensors, which can result in incorrect detection of reference surfaces.
Innovation Solution
A mobile computing device equipped with a stereo camera assembly and an auxiliary sensor, such as an IMU, uses a gravity vector to determine an inclination angle, applying a constraint to plane fitting operations to accurately detect reference surfaces, thereby enhancing the detection of object dimensions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If stereo imaging is used to detect surfaces of objects, then dimensioning capability is provided, but detection accuracy deteriorates under certain conditions such as low point cloud density
Solution Approach 1:
The patent introduces an auxiliary sensor (IMU) as an intermediary device that provides gravity vector information to constrain the plane fitting operation. This mediator bridges the gap between stereo imaging data and reference surface detection, enabling accurate detection even when point cloud density is low by using the gravity vector as an additional constraint.
Solution Approach 2:
The patent changes the parameters used in plane fitting by incorporating the inclination angle derived from the gravity vector as a constraint. This parameter change transforms the unconstrained plane fitting problem into a constrained optimization problem, improving detection accuracy under challenging conditions.
2Measurement precision
If conventional plane fitting is used without constraints, then detection flexibility is maintained, but reference surface detection accuracy deteriorates when gravity vector is offset or floor is not perpendicular
Solution Approach 1:
The patent applies parameter changes by incorporating the inclination angle as a constraint parameter in the plane fitting operation. This allows the system to adapt to various floor orientations by adjusting the constraint based on the gravity vector, maintaining both precision and adaptability.
Solution Approach 2:
The patent introduces dynamics by making the plane fitting constraint adaptive rather than static. The inclination angle constraint is dynamically determined from the gravity vector, allowing the system to adapt to different floor orientations and conditions in real-time.
3Measurement precision
If motion sensor calibration is assumed accurate, then system complexity is reduced, but detection accuracy deteriorates when miscalibration occurs
Solution Approach 1:
The patent uses the auxiliary sensor as an intermediary to provide an independent reference (gravity vector) that constrains the plane fitting. This intermediary provides a check on motion sensor accuracy, improving dimensioning accuracy even when miscalibration occurs, while adding manageable complexity.
Data Source
AI summary
A method includes: obtaining a reference stereo image from a stereo camera assembly of a mobile computing device; detecting a reference surface from the reference stereo image; determining an inclination angle of the reference surface relative to an output vector of an auxiliary sensor of the mobile computing device; obtaining a first dimensioning stereo image from the stereo camera assembly; detecting the reference surface in the first dimensioning stereo image based on the inclination angle; detecting a first object surface in the first dimensioning stereo image; and generating dimensions of the object based on the first object surface and the reference surface.